Review Not peer-reviewed version

Machine Learning Techniques for

Coffee Classification: A Comprehensive
Review of Scientific Research

Isabela V. de C. Motta * , Nicolas Vuillerme , Huy-Hieu Pham , Felipe Augusto Pereira de Figueiredo

Posted Date: 21 June 2024

doi: 10.20944/preprints202406.1462.v1

Keywords: artificial intelligence; coffee bean and leaves classification; computer vision; machine-learning

Preprints.org is a free multidiscipline platform providing preprint service that

is dedicated to making early versions of research outputs permanently
available and citable. Preprints posted at Preprints.org appear in Web of
Science, Crossref, Google Scholar, Scilit, Europe PMC.

Copyright: This is an open access article distributed under the Creative Commons
Attribution License which permits unrestricted use, distribution, and reproduction in any
medium, provided the original work is properly cited.
Preprints.org (www.preprints.org) | NOT PEER-REVIEWED | Posted: 21 June 2024 doi:10.20944/preprints202406.1462.v1

Disclaimer/Publisher’s Note: The statements, opinions, and data contained in all publications are solely those of the individual author(s) and
contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to people or property resulting
from any ideas, methods, instructions, or products referred to in the content.

Article
Machine Learning Techniques for Coffee Classification:
A Comprehensive Review of Scientific Research
Isabela V. de C. Motta 1, *, Nicolas Vuillerme 2 , Huy-Hieu Pham 3 , Felipe A. P. de Figueiredo 1
1 National Institute of Telecommunications, Av. João de Camargo, 510, Santa Rita do Sapucaí 37540-000, Minas Gerais, Brazil;
[email protected]
2 AGEIS, Université Grenoble Alpes, Grenoble 38000, France; [email protected]
3 College of Engineering & Computer Science and VinUni-Illinois Smart Health Center, VinUniversity, Hanoi,Vietnam;
[email protected]
* Correspondence: [email protected]

Abstract: In the realm of agribusiness, transformative shifts are underway, propelled by the growing demands
and expanding scales of grain production. This evolution calls for a critical reevaluation of the existing paradigms
in coffee production and marketing paradigms, with a specific focus on integrating Artificial Intelligence (AI).
This work aims to review, synthesize, and summarize the available data regarding how Machine Learning (ML)
has been used to detect and classify characteristics in coffee beans and leaves. For this purpose, a comprehensive
literature review of the most significant research contributions describing the application of AI for advanced
classification techniques in coffee agriculture has been carried out. Our analysis suggests that implementing AI
technologies allows the classification of coffee, encompassing various attributes such as maturity, roast intensity,
disease identification, flavor profiles, and overall quality. More largely, this technological advancement holds the
potential to revolutionize coffee farming by providing producers and agricultural specialists with sophisticated
tools to enhance production efficiency, minimize costs, and improve the accuracy and confidence of their decision-
making processes. This article allows us to learn about the latest studies in ML in the coffee area, observe the
methodology used, and allow researchers to develop new research that covers gaps in the literature, bringing a
real contribution to the scientific field. Furthermore, this article listed the databases used in the studies and which
may be useful for future ML projects.

Keywords: artificial intelligence; machine-learning; computer vision; coffee bean and leaves classification

1. Introduction
Coffee stands as a cornerstone crop globally and its consumption has been increasing in recent
years. [1]. This surge underscores coffee’s pivotal role in the global market, given its status as a crucial
economic food commodity [2].
Current methodologies for managing agricultural data in coffee farming are increasingly consid-
ered outdated—labor-intensive, time-consuming, and, most importantly, prone to inaccuracies and
errors. In this context, the advent of Machine Learning (ML) and intelligent data analytics emerges as a
transformative force, propelling sustainable agriculture by enhancing food production and addressing
the pressing challenges in this sector [3].
Although a considerable volume of work addresses the use of Artificial Intelligence (AI) in coffee
culture, it should be noted that research has followed different paths, depending on its various aspects.
There is a considerable volume of work on the use of AI in agriculture, especially in the category of
predictive analysis [4]. Indeed, there are numerous areas in coffee production where ML techniques
can be applied. Intelligent systems can provide advances and improvements, from grain harvesting
to commercialization. In a scenario where specialized systems surpass human diagnoses in terms of
trust, speed, and accuracy, it will be of fundamental importance for coffee growers to make their use
widely applicable and essential to increase productivity in agriculture.
Therefore, the present work aims to review and summarize the available data regarding how ML
has been used in coffee production and marketing in classification activities, which encompass the
classification of defects, roasting, maturation, and sensory characteristics of coffee beans and also leaf

© 2024 by the author(s). Distributed under a Creative Commons CC BY license.

Preprints.org (www.preprints.org) | NOT PEER-REVIEWED | Posted: 21 June 2024 doi:10.20944/preprints202406.1462.v1

2 of 34

diseases that affect the coffee plantation. This research is important and justified by understanding
the relationship between AI and coffee production, identifying trends in AI applications in coffee
classification, and, mainly, identifying research gaps that can be eliminated to improve processes
throughout the coffee production chain.
Considering that global coffee consumption is increasing, and its importance of participation
in revenue in more than 70 developing countries economies [1], combined with the capacity of AI
techniques for problem-solving and decision-making, this paper presents a detailed summary of
research covering coffee and AI.
Table 1 compares our literature and related literature reviews. The first column corresponds
to the reference of the literature review; the second column describes the paper; the third column
lists the number of papers analyzed in the work; and the last column informs the time range of the
analyzed works. The review’s authors [5] analyzed seven studies that classify the quality and type
of coffee beans based on images and using ML. The reviews [6–8] analyze research works and list
challenges of disease detection of various plants. The literature review [6] focuses on leaf diseases. The
study of [9] analyzes technologies for detecting roast-level coffee beans, but not all studies use ML
techniques. Many studies related to smart agriculture [10,11] address machine learning techniques for
classifications of other types of crops, such as rice [12–15], corn [16,17] and soybean [18].

Table 1. Related Literature Reviews

Reference Brief Description Quantity Year

[5] Machine learning techniques for classifying the quality 7 2018-2022
and types of coffee beans on image-based.
[6] Machine learning techniques for detecting leaf diseases in 118 2010-2022
various plants.
[7] Machine learning techniques for detecting diseases in vari- 160 2017-2022
ous plants.
[9] Techniques for the detection of Coffee Bean Roasting Lev- 31 2014-2022
els.
[8] Machine learning techniques for detecting disease in vari- 135 2017-2023
ous plants.

A Comprehensive Review was used to achieve the proposed objective of synthesizing and
understanding how ML techniques for coffee classification are presented in scientific research. The
review was carried out in the IEEE, Science Direct, and Springer databases, with terms compatible
with the object of this research.
The main goal of this review is to survey current research in the coffee area that uses machine and
deep learning techniques. This research lists the works related to the classification of coffee beans and
leaves in a comprehensive way. In this context, our main contributions include:

• A more up-to-date and comprehensive literature review of current ML research in the classi-
fication and detection of coffee beans and coffee leaves, covering 72 papers and different ML
algorithms, including comparisons and discussions among them;
• An analysis of the evaluation metrics used in ML for classification and detection of coffee beans
and coffee leaves for understanding results and reproducing them, benefiting future research;
• A presentation of architectures used based on ML for detecting and classifying coffee beans and
coffee leaves;
• A detailed exploration of the main limitations, challenges, and future directions related to the
use of ML techniques for the classification and detection of coffee beans and coffee leaves;
• A summary of the databases used in research to detect and classify coffee beans and coffee leaves.

This work was divided into five more sections to contextualize the use of ML in coffee farming,
specifically its use on coffee beans and leaves. Following this introduction, the second section describes
Preprints.org (www.preprints.org) | NOT PEER-REVIEWED | Posted: 21 June 2024 doi:10.20944/preprints202406.1462.v1

3 of 34

the research strategy and details the important points of each selected study. The third section
introduces the main ML techniques used for classification tasks. The fourth section summarizes
and analyzes the findings, presents the importance of coffee classification in the coffee industry, and
demonstrates how agribusiness uses ML techniques. The fifth section discusses the studies’ challenges,
future trends, and limitations and summarizes the dataset for classification tasks. Finally, the sixth
section presents the final considerations.

2. Methodology
This paper is a descriptive research of the comprehensive review type carried out through online
access to the IEEE, Science Direct, and Springer databases. In the browsing for research articles,
the descriptors "machine learning" and "coffee." For the inclusion of works in the present study, the
following criteria were established: articles published in the last five years before the consultation,
articles in which the topic of "machine learning" is related to coffee classification techniques, and
articles available in full format in the databases above. Theoretical studies and systematic literature
reviews were not included in the overview of synthesized research data.
The article analysis process followed these steps: 1) search for descriptors in the databases above;
2) exclusion of articles published more than five years ago; 3) exclusion of works with low relevance; 4)
critical reading of the articles and checking whether they meet the proposed theme; 5) exclusion of
theoretical articles and literature reviews; 6) final analysis. After selecting the articles using inclusion
and exclusion criteria, tables containing the main information about the objectives and scenario of
application, the methodology used for coffee classification analysis, and the results were created.
In the IEEE database, 114 articles were found with the words “machine learning” and “coffee”.
Fifty-eight (58) articles were disregarded because they were unrelated to the coffee area; for example,
the author’s last name is Coffee or the three searched words do not appear simultaneously in the text.
Only "machine learning", or only "coffee". Ten (10) articles were disregarded because they were not
related to classifying coffee beans, such as Predicting Coffee Crop Yield, detecting coffee trees, coffee
price prediction, and agriculture 4.0. Finally, two (2) articles were disregarded in the analysis because
it was a literature review. In the same way, in the Science database, 2,828 articles were found; 2,770
were disregarded because it was not related to the general theme; 34 were disregarded because it was
not related to the specific theme; and two (2) articles were disregarded in the analysis because it was
a literature review. In summary, 7,630 articles were found in the Springer database, but 7,617 were
disregarded; 6 were disregarded because they were unrelated to the specific theme; and 1 article was
disregarded in the analysis because it was a literature review. Figure 1 shows the research methodology
used in this study. Figure 1 shows the total number of publications per database and the steps used to
choose the selected publications.
Preprints.org (www.preprints.org) | NOT PEER-REVIEWED | Posted: 21 June 2024 doi:10.20944/preprints202406.1462.v1

4 of 34

IEEE • STEP 1: 114 articles were found with words “machine learning” and coffee; IEEE
• STEP 2: 58 articles were disregarded because they were not related to the
coffee classification area;
• STEP 3: 10 articles were disregarded because it were not related to classifying
coffee beans;
114 publication 44 publication
• STEP 4: 2 articles were disregarded in analysis because was literature review.

SCIENCE • STEP 1: 2,828 articles were found with words “machine learning” and coffee; 72 selected
SCIENCE
• STEP 2: 2,770 articles were disregarded because they were not related to the publicacions
coffee classification area;
• STEP 3: 34 articles were disregarded because it were not related to classifying
coffee beans;
2,828 publication 22 publication
• STEP 4: 2 articles were disregarded in analysis because was literature review.

SPRINGER • STEP 1: 7,630 articles were found with words “machine learning” and coffee; SPRINGER
• STEP 2: 7,617 articles were disregarded because they were not related to the
coffee classification area;
• STEP 3: 6 articles were disregarded because it were not related to classifying
coffee beans;
7,630 publication 6 publication
• STEP 4: 1 articles were disregarded in analysis because was literature review.

Figure 1. Research Methodology

In Figure 2, we can see a fluctuation in the number of publications over the last five (5) years,
which various factors may have influenced. In general, the number of publications has increased over
the years.

Publication Year

28
23

10
5 6

2019 2020 2021 2022 2023

Figure 2. Number of Articles Selected

Additionally, Table 2 below shows the number of publications per database searched. As illus-
trated, the first column corresponds to the database, and the second column describes the number of
publications.

Table 2. Number of Publication per Database.

Database Number of Publica-

tion
IEEE 44
Science 22
Springer 6
TOTAL 72
Preprints.org (www.preprints.org) | NOT PEER-REVIEWED | Posted: 21 June 2024 doi:10.20944/preprints202406.1462.v1

5 of 34

2.1. Research Questions

This review was designed to answer twelve Research Questions (RQ). The RQ are as follows.
RQ1: What are the most used architectures based on ML for detecting and classifying defects in
coffee beans?
RQ2: What are the most used architectures based on ML for detecting and classifying coffee
beans roasting?
RQ3: What are the most used architectures based on ML for the sensory classification of coffee?
RQ4: What are the most used architectures based on ML for detecting and classifying the maturity
of coffee beans?
RQ5: What are the most used architectures based on ML for detecting and classifying coffee diseases?
RQ6: What defects are considered when classifying the coffee bean in the studies?
RQ7: What stages are considered to classify coffee roasting in the works studied?
RQ8: What stages are considered to classify coffee maturity in the works studied?
RQ9: What are the different coffee diseases addressed in the works studied?
RQ10: What challenges exist, and how can research be improved in detecting and classifying
coffee beans and leaves based on the studies reviewed?
RQ11: How diverse is the research on coffee bean and coffee leaves detection or classification,
and for what classification purpose are ML applications the most?
RQ12: Which databases are available for research into detecting and classifying coffee beans and
coffee leaves?
The questions RQ1, RQ2, RQ3, RQ4, RQ5, RQ6, RQ7, RQ8, and RQ9 aim to map the most used
architectures for ML in coffee bean classification and, consequently, classify commonly used ML
approaches to resolve them. Based on this review, these five questions identify the main ML algorithms
and their main metrics used to achieve the classification objective. In these questions, it is possible to
carry out a quantitative and qualitative analysis of the more effective ML algorithms to be applied to
coffee bean classification. Through mapping, it is possible to identify how researchers are addressing
the techniques that involve ML and consequently analyzing potential gaps related to the topic.
By answering RQ10, RQ11, and RQ12, we can understand the challenges, future trends, and
final observations when implementing ML techniques in various coffee bean and coffee leaves
classification scenarios.
Finally, RQ1 and RQ6 are answered in Subsection 4.1, RQ2 and RQ7 in Subsection 4.2, RQ3 in
Subsection 4.3, RQ4 and RQ8 in Subsection 4.4, RQ5 and RQ9 in Subsection 4.5, and RQ10, RQ11 and
RQ12 in Section 5.

3. Machine Learning Techniques for Coffee Classification

ML is an area of AI capable of generalizing a problem from a set of training data to correctly
classify or predict data that has not been previously observed [19]. It is a tool that can be applied to
any field that needs data analysis.
There are three ML techniques: unsupervised, supervised, and reinforcement learning. A training
set is observed in supervised learning and comprises examples of input and output pairs. The
machine learns a function that maps the input to the output, and this function is called the hypothesis
function [20]. The supervised learning problem can be classified when the output value has finite
values or regression when the output value has infinite values. The idea of classification involves
grouping items into classes or groups. The difference between supervised and unsupervised learning
can be seen in Figures 3 and 4 below.
Preprints.org (www.preprints.org) | NOT PEER-REVIEWED | Posted: 21 June 2024 doi:10.20944/preprints202406.1462.v1

6 of 34

Figure 3. Supervised Learning. Adapted from [21]

Figure 4. Unsupervised Learning. Adapted from [21]

Computer vision is an area of AI that seeks to analyze, interpret, and extract relevant information
from images so that decisions can be made. Object recognition in its complete generality is difficult [20].
Convolutional Neural Network (CNN) is a ML model that extracts features in various computer vision
tasks like image classifications. Several CNN architecture models, such as AlexNet, VGGNet, ResNet,
MobileNet, EfficientNet, and DenseNet, are used for image classifications. The Figure 5 shows a
typical CNN.

Figure 5. A Typical CNN. Adapted from []

Vision Transformer is a neural network with the potential for extensive use in image classification
tasks [22]. The Figure 6 shows a illustration of the Vision Transformer Model.
Preprints.org (www.preprints.org) | NOT PEER-REVIEWED | Posted: 21 June 2024 doi:10.20944/preprints202406.1462.v1

7 of 34

Figure 6. Vision Transformer Model. Adapted from [23]

ML techniques combined with computer vision have become decisive in developing agricultural
efficiency and have been widely applied in research in various areas of agriculture [24], including
coffee farming. Due to different algorithms, this research seeks to identify which models achieve
greater accuracy in image classification.

4. Overview of Synthesized Research Data

This section summarizes the most significant studies on ML in coffee classification. It details each
study, including the reference (authors and publication year), objectives and application scenarios,
methodology (architectures and dataset), and main results.
We identified 72 selected studies that could be grouped into 5 common themes: classification of
(1) coffee defects, (2) coffee roasting, (3) coffee aroma and flavor, (4) coffee maturity, and (5) coffee
diseases. The 5 categories are listed and commented below.

4.1. Coffee Defects Classification

Defects and impurities in coffee beans reduce their quality. Defective beans affect the flavor of
the coffee and, therefore, devalue it and affect the producer’s profitability. Several factors can cause
these defects, such as problems in production and storage and physiological and genetic changes.
Identifying defects makes it possible to improve management and prevent the occurrence of these
defects, which depreciate the coffee.
As illustrated in Tables 3 and 4, the first column corresponds to the reference of the literature
review; the second column describes the main objectives of the paper; the third column lists the models
and algorithms used in the paper; and the last column informs the results achieved.
Preprints.org (www.preprints.org) | NOT PEER-REVIEWED | Posted: 21 June 2024 doi:10.20944/preprints202406.1462.v1

8 of 34

Table 3. Coffee Defects Classification.

Reference Objectives and Scenario of Application Methodology Results

[25] The study created an inspection machine to classify Three deep learning models (Enhanced, ResNet-50, The most efficient model was ResNet-50, with an
defects in coffee beans. and AlexNet) are used to analyze the images. accuracy of 93.33%.
[26] The study presents a system for inspecting coffee The model uses DenseNet201 architecture. The proposed system achieved 98.97%.
beans, identifying good and bad ones.
[27] The study explores automated detection of the qual- The model uses a Support Vector Machine (SVM), The method was evaluated using cross-validation
ity of coffee beans based on their color and texture Deep Neural Network (DNN), and Random Forest with K-Fold of 5 and 10. The highest accuracy value
characteristics. (RF). achieved was 96.11%.
[28] The study proposes a scheme for the automated The model is based on a generative adversarial More than 90% of the labeling time is done by the
inspection of defects in dense Arabica coffee beans. network (GAN) and can generate synthetic training proposed prototype, which uses less time than a
images with defects at multiple locations. human for the same task.
[29] The study presents a new dataset containing 8,000 The model was implemented with two CNN archi- The final average test accuracy was 81.12% for
images of green Arabica coffee beans divided into 4 tectures: ResNet-18 and MobileNetV2. ResNet-18 and 81.31% for MobileNetV2.
classes: Peaberry, Longberry, Premium, and Defect.
[30] The study categorizes coffee beans into seven The proposed CNN model has 12 layers. The The proposed model achieved an accuracy rate
classes: sour, black, broken, moldy, shell, insect dataset has about 1,700 images in each folder. greater than 90% for all categories except shell
damage, and good beans. beans (88%).
[31] The study classifies images of coffee beans as defec- The proposed CNN model has three convolution The model achieved an accuracy of 90.44%.
tive or normal. layers with three max-pooling layers and three fully
connected layers. A dataset of 1,813 images and
two classes was used.
[32] The study proposes a system called Hough circle as- The proposed method uses the Hough Circle Trans- The proposed scheme achieved half of the testing
sisting deep-network inspection scheme (HCADIS) form algorithm, an image processing method that images greater than 80% in defect inspection accu-
which identifies defects in coffee beans. detects circles in an image. racy values.
[33] The study classifies defects in coffee beans into four The proposed method uses the Mask R-CNN The proposed method obtained an accuracy of
classes: black, broken, holey, and normal. (Region-based CNN) algorithm. A dataset of 480 93.3% for tests with individual objects and 75% for
images with two forms of images was used: images tests with multiple objects.
with individual coffee beans and images with mul-
tiple objects.
Preprints.org (www.preprints.org) | NOT PEER-REVIEWED | Posted: 21 June 2024 doi:10.20944/preprints202406.1462.v1

9 of 34

Table 4. Coffee Defects Classification.

Reference Objectives and Scenario of Application Methodology Results

[34] The study presents a method to detect defects in Spectral and spatial characteristics were extracted The model presented an overall accuracy of 98.6%
green coffee beans in four categories: healthy, black, from the images, and ML algorithms were applied using SVM with dimensionality reduction and
insects damaged, and shell. to classify the coffee beans. band selection.
[35] The study classifies green coffee beans as special or Coffee samples were collected from different re- The SVM model obtained the best performance,
traditional. gions of Brazil, and a multispectral camera cap- with an accuracy of 97.5%, followed by MLP with
tured images of the beans at different wavelengths. 96.9%, RF with 95.6%, and KNN with 94.4%.
Four ML models were used: SVM, K-Nearest
Neighbors (KNN), RF, and Multilayer Perceptron
(MLP).
[36] The study classifies two types of coffee bad beans: The model was based on NFNet-F3, which com- The proposed model achieved an F1-score of
insect bite and broken. bines semi-supervised learning. 97.21% and a precision of 97.38%.
[37] The study classifies three types of coffee bean The transfer learning models used were: The best model was Squeezenet, with an average
species: espresso, Kenya, and Starbucks Pike Place. SqueezeNet, Inception V3, VGG16, and VGG19. A classification success of 87.3%.
dataset of 1,554 images was used.
[38] The study identifies Arabica and Robusta coffee The proposed model used four convolution layers, The CNN developed achieved an accuracy rate of
types through the images of the leaves. four pooling layers, and a fully connected layer. 97.67% better than other nets.
It was compared with LeNet, AlexNet, ResNet-50,
and GoogleNet. A dataset of 19,980 images was
used.
[39] The study presents a system that classifies different The proposed model adjusted a Slim-CNN using The lightweight model achieved an accuracy of
kinds of coffee beans: Normal beans, Peaberries, the least parameters. A dataset of 5,435 images was 92%.
insect-infested, black beans, shell beans, and sour used.
beans.
[40] The study presents a new dataset that classifies 17 Two CNN architectures were tested: MobileNet with InceptionResnetV2, the classification for 17
different defects of coffee beans. and InceptionResnetV2. Two datasets were used. classes achieved an accuracy of 53.35%, and for 3
classes, it achieved 92.52%.
[41] The study classifies palm civet coffee beans based The neural network model has an input layer with The proposed model achieved an accuracy of
on their mass spectra. 301 neurons, and the hidden layer has 50 neurons. 99.58%.
[42] The study classifies good-quality raw coffee beans The model compares VGG16 and Inception V3. A The best model was Inception, which achieved an
and subpar-quality raw coffee beans dataset of 100 images was used. accuracy of 99%.
[43] The study classifies 4 Arabica coffee bean varieties: Five classification methods was tested: Artificial The best model was ANN, wich achieved an accu-
Aceh Gayo, Bali Kintamani, Lintong, and Surya Neural Network (ANN), Decision Tree (DT), KNN, racy of 99.75%.
Sabana Selo. Naive Bayes, and SVM. A dataset of 400 images
was used.
[]
[]
[]
[]
[]
Preprints.org (www.preprints.org) | NOT PEER-REVIEWED | Posted: 21 June 2024 doi:10.20944/preprints202406.1462.v1

10 of 34

Most coffee defect classification research consists of categorizing coffee according to effective
beans of an intrinsic nature (imperfect beans), which are beans damaged by the imperfect application
of agricultural processes such as improper drying or picking of overripe cherries [44]. These coffee
beans are black, broken, and damaged by insects, including the coffee borer beetle.
The challenge in future research in defect classification is to cover all defects originating from
coffee cultivation. Few studies have identified external defects in the coffee bean, such as the presence
of sticks, stones, clods, bark, and small insects. These defects originate during harvesting due to coffee
falling on the ground and poor fanning. In the same way, few studies have identified acidic coffees
derived from prolonged fermentation.
The paper [30] classified 6 types of coffee intrinsic and extrinsic defects. The authors created a
screening system with a user interface. The authors of [34] created a high-speed near-infrared (NIR)
camera to capture images of coffee beans moving on a conveyor belt. [25] also proposed a conveyor
for capturing and uploading images.
[26] used an automated system to classify good and bad coffee beans. The bad coffee beans are
divided into three categories: broken, insect-infested, and mold. The system recognizes the coffee
beans; if all classification results are negative, the coffee bean is considered good and kept. If at least
one output indicates a defect, the coffee bean is labeled with the corresponding type of defect. [28]
classified all defects categorized by the Specialty Coffee Association of America (SCAA).
Meanwhile, [27] developed a Python algorithm to extract texture, shape, and color characteristics
from images of coffee beans. Specialty coffees go through a more laborious production process, require
special care from planting to roasting, and are made of pure, unmixed, high-quality coffees. At the
same time, traditional coffee has inferior and defective beans. This mixture reduces the quality of the
coffee as it changes its flavor and reduces its cost. [35] classified coffee beans in different regions of
Brazil as special or traditional. The papers [38] and [37] classify coffee bean species. [38] classified
arabica and robusta coffee plants, and [37] classified espresso, Kenya, and Starbucks pike place species.
The networks tested for classifying coffee defects were Resnet-50, Densenet201, SVM, DNN, RF,
GAN, MobilenetV2, Hough Circle Transformer, Mask R-CNN, NFNet-F3, SqueezeNet, Slim-CNN,
InceptionResnetV2, ANN , InceptionV3 and CNN networks proposed by the researches authors.
Enhanced, AlexNet, ResNet-18, KNN, MLP, VGG-16, VGG-19, MobileNet were also tested, but
obtained inferior results when compared to other networks.
The highest accuracy achieved was 99.58% for the ANN network proposed by the work (tsai,
2023). Tsai’s study combines ANN with Mass Spectrometry and analyzes 2 classes of single beans:
civet coffee beans and regular beans. It is not possible to say which network model presents the best
performance among all the researches analyzed because the databases tested were different. The works
differ in the defects they seek to classify and consequently in the number of classes presented in each
model. The researches used datasets from 100 images to around 20,000 images. The size of the dataset
also influences the model result.

4.2. Coffee Roast Classification

Coffee roasting is one of the final stages of production and a determining factor in producing a
good drink. Good roasting highlights the characteristics of each type of bean, which are flavor, aroma,
and acidity. The same coffee bean may have different characteristics depending on the type of roast.
The color of the coffee bean and the aroma can differentiate roast levels. The coffee beans change color
as the temperature increases, and the roast can be light, medium, or dark. Each of them will have
different flavor characteristics.
Roasting is defined by the time the coffee bean remains at a high temperature under the careful
supervision of a specialized professional. Work that classifies the roasting level and analyzes the
process until the coffee reaches the final carbonization stage contributes to automating the process
without professional supervision.
Preprints.org (www.preprints.org) | NOT PEER-REVIEWED | Posted: 21 June 2024 doi:10.20944/preprints202406.1462.v1

11 of 34

As illustrated in Table 5, the first column corresponds to the reference of the literature review; the
second column describes the paper’s main objectives; the third column lists the models and algorithms
used in the paper; and the last column informs the results achieved.
Preprints.org (www.preprints.org) | NOT PEER-REVIEWED | Posted: 21 June 2024 doi:10.20944/preprints202406.1462.v1

12 of 34

Table 5. Coffee Roast Classification.

Reference Objectives and Scenario of Application Methodology Results

[45] The study classifies Arabica coffee beans based on The work proposes two main procedures: feature The polynomial kernel achieved a maximum accu-
their light, medium, and dark roast levels. extraction and classification. Four kernel types are racy of 100% using k-fold values of 5 and 10.
used in the SVM method for classification: linear,
polynomial, radial basis, and sigmoidal.
[46] The study presents a method to classify the quality A dataset of 160 images was used. The proposed The best model was ResNet-152, wich achieved an
of coffee beans based on their roast level: good, model was tested with ResNet-152 and VGG16. accuracy of 73.3%.
medium, and bad.
[47] The study presents a coffee roasting process to clas- The model used Android smartphones and a The best model was MobileNetV2, which achieved
sify three classes of roast coffee beans: accepted, dataset of 10,944 images. The model tested an accuracy of 97.75%.
rejected, and not yet. MobileNetv1, MobileNetV2, NasNetMobile, and
DenseNet121 architectures.
[48] The study presents a method that recognizes the The model was tested with 5 algorithms: linear The fully connected neural network performed the
brightness of the beans before and after grinding. regression, DT, RF, support vector regression, and best, with 2.52 of color numerical difference.
fully coupled neural network.
[49] The study presents a method that searches for opti- Starling particle swarm optimization (SPSO) and SPSO achieved performance superior to other algo-
mal coffee bean roasting conditions. other swarm intelligence and gradient-based algo- rithms with average errors of 1.2–8.5%.
rithms were used.
[50] The study presents a method to recognize the dif- The model used the Densenet121 architecture. A The proposed model achieved an accuracy of
ferent grades of coffee beans based on their features dataset of 363 images was used. 81.89%.
and patterns.
[51] The study presents a method to detect the roast The model developed the board using CNN archi- The proposed model achieved an accuracy of
level of coffee beans. tecture and NVIDIA Jetson Nano. A dataset of 91.33%.
2,489 images was used with three classes: under-
roasting, optimum-roasting, and over-roasting.
[52] The study presents a method to detect the roasting The study proposed a CNN to classifies 4 roasting The CNN proposed achieved an accuracy of 97.5%.
level of coffee beans into 4 classes. levels: green, light roast, medium roast, and dark
roast. A dataset of 1,200 images was used.
Preprints.org (www.preprints.org) | NOT PEER-REVIEWED | Posted: 21 June 2024 doi:10.20944/preprints202406.1462.v1

13 of 34

The authors of papers [46,47] developed a mobile application that automatically classifies coffee
bean quality based on its roast degree.
Additional work has been carried out on the automated diagnosis of coffee roasting level, achiev-
ing excellent results. [45] achieved a maximum 100% accuracy in classifying Arabica coffee into light,
medium, and dark. To predict the roasting degree of coffee beans, the authors of [48] created a model
that consists of 4 input data: temperature, humidity, place of origin, and temperature of the roasting
curve sampled every 15 seconds.
The networks tested for coffee roast classification were SVM, ResNet-152, MobileNetV2, Fully
Connected Neural Network, SPSO, DenseNet121, and CNN proposed by the research authors.
VGG16, MobileNetV1, NasNetMobile, Linear Regression, DT, RF, Support Vector Regression, and
Fully Couped Neural Network were also tested, but obtained inferior results when compared to other
network models.
The research by (Septiarini, 2022) achieved maximum accuracy to classify 3 roast levels using
SVM. It is not possible to say which network presents the best performance among all the works
analyzed because the databases tested were different. The works differ in the roast levels they seek to
classify and consequently in the number of classes presented in each model. The studies studied used
datasets from 160 images to around 11,000 images. The size of the dataset also influences the model
result. More studies are needed to consider different coffee roasting levels.

4.3. Coffee Sensory Classification

During coffee production, the beans can go through different processes. While traditional coffee
has undesirable characteristics such as firm bitterness, special coffees have a diverse range of flavors
and aromatic notes and are better balanced. Sensory analysis of coffee involves identifying its prop-
erties in the drink. The method takes place when the taster separates, inhales, and ingests a small
amount of roasted and ground coffee and evaluates the following sample factors: Fragrance, Aroma,
Uniformity, Sweetness, Flavor, Acidity, Body, Finish, and Balance.
As illustrated in Table 6, the first column corresponds to the literature review’s reference; the
second column describes the paper’s main objectives; the third column lists the models and algorithms
used in the paper; and the last column informs the results achieved.
Preprints.org (www.preprints.org) | NOT PEER-REVIEWED | Posted: 21 June 2024 doi:10.20944/preprints202406.1462.v1

14 of 34

Table 6. Coffee Sensory Classification.

Reference Objectives and Scenario of Application Methodology Results

[53] The study explores how to classify and characterize The SVM method was used with an electronic nose The proposed model achieved an accuracy of 70%.
coffee beans based on their aroma. system and a dataset with 100 coffee bean samples.
[54] The study proposes the use of an electronic nose Nine different mixture combinations were used for The best model was KNN, which achieved an accu-
(E-nose) to recognize original Arabica civet coffee a total of 90 samples. Three classification methods racy of 97.77%.
(authentic and non-authentic). were compared: Logistic Regression (LR), Linear
Discriminant Analysis (LDA), and KNN.
[55] The study presented a new technique to analyze A miniaturized potentiometric electronic tongue The proposed model achieved an accuracy of 91.3
and characterize the flavor of 21 varieties of coffee. based on low-selectivity polymeric sensors was %.
used.
[56] The study used an e-nose device to estimate the The methods used were PCA (principal component PLSR and ANN models achieved an R2 of 0.9576
caffeine content of samples. analysis), LDA, PLSR (partial least squares regres- and 0.9634, respectively, and the LDA model
sion), and ANN. Seven coffee bean classes and a achieved an R2 of 0.9714.
total of 147 samples were made.
[57] This study presents a model for predicting cup cof- Two algorithms were implemented: SVM and The most efficient model was ANN, which had an
fee quality. ANN. Fifty-six samples were analyzed. average accuracy of 81%.
[58] This study presents a model for coffee aroma clas- The model used an electronic nose that combined The proposed model achieved an accuracy of 100%.
sification. the separability indicator and the support vector
machine margin. It collected data on the coffee
aromas of two coffee brands.
[59] The study compares coffee quality to recommend The paper compares various regression models us- The best model achieved an MAE of 0.2567.
the best coffee combination based on various fea- ing cross-validation. The models included Linear
tures related to aroma. Regression, Ridge, Lasso, ElasticNet, DT Regressor,
Random Forest Regressor, Gradient Boosting Re-
gressor, Support Vector Regressor (SVR), and MLP
Regressor.
Preprints.org (www.preprints.org) | NOT PEER-REVIEWED | Posted: 21 June 2024 doi:10.20944/preprints202406.1462.v1

15 of 34

The models for finding the sensory characteristics of coffee (aroma and flavor) do not use images,
these studies employ a dataset with coffee samples and can use an electronic tongue or nose. The
electronic nose (e-nose) has gas sensors that can identify patterns when combined with MA algorithms.
The dataset of these studies is composed of samples of coffee odors collected by the gas sensors present
in the e-nose. The samples are submitted to machine learning algorithms to recognize and classify the
coffee brand [58] and coffee bean types [56]. [53,54,56,58] classified coffee beans based on their aroma
using an e-nose. The method proposed by [58] achieved 100% accuracy for classifying two distinct
coffee brands using odor samples collected by e-nose gas sensors. The electronic tongue (e-tongue) has
low-selective potentiometric sensors that respond to a wide variety of flavors. [55] classified the taste
of coffee using an e-tongue and achieved excellent results. The dataset [55]’s research is composed of
coffee cup samples prepared by a coffee machine, and the model identifies 21 varieties of coffee and
achieves an average accuracy of 91.3%. The study [57] classified the quality of coffee drinks based on
measurements made to almond and roasted coffee beans. [59] used a sensory evaluation of the coffee
quality scores dataset with features related to aroma, flavor, acidity, body, balance, uniformity, and
others using various linear regression models to predict coffee quality scores.
The networks tested for coffee sensory analysis were SVM, KNN, PLSR, LDA, ANN, SVM and
various Regressions Models. It is not possible to say which network presents the best performance
among all the works analyzed because the techniques used were different (e-nose and e-tongue) and
the databases tested were also different.

4.4. Coffee Maturity Classification

Coffee maturation begins with the fruits turning light green, evolving into cherry fruits ready to
be harvested. The previous year’s flowering influences fruit maturation and is directly associated with
the quality of the drink. Identifying the maturity of the coffee is very important because the coffee
must be harvested with the highest percentage of ripe ”cherry” fruits to provide the best quality drink.
Research in coffee classification must consider the ability to generalize to other coffee-producing
regions and different coffee varieties. The characteristics extracted from the images may not capture
all the nuances of coffee maturity.
As illustrated in Table 7, the first column corresponds to the literature review’s reference; the
second describes the papers’s main objectives; the third lists the models and algorithms used in the
paper; and the last column informs the results achieved.
Preprints.org (www.preprints.org) | NOT PEER-REVIEWED | Posted: 21 June 2024 doi:10.20944/preprints202406.1462.v1

16 of 34

Table 7. Coffee Maturity Classification.

Reference Objectives and Scenario of Application Methodology Results

[60] The study presents a framework for classifying cof- Five CNN architectures were validated: VGG16, DenseNet201 achieved an accuracy over 98%.
fee cherry fruits into 5 ripening stages. VGG19, Inception-ResNet-V2, Inception-V3, and
DenseNet201 on a dataset with 600 images.
[61] The study explores the classification of coffee cher- The model used the KNN algorithm and ANN in a The best model achieved with KNN an accuracy of
ries as green, half broken, nosimetrics, and red. dataset of 1,159 images. 72.12%.
[62] The study classifies the type and maturity of the The article compares the performance of two mod- The ResNet50 model performed best and achieved
coffee. els, the Deep-CNN and ResNet50. an accuracy of 99.01%.
[63] The study presents a method to monitor the The model used a UAV with a modified multispec- The NDVI (Normalized Vegetation Index) corre-
ripeness of coffee fruits using multispectral images tral camera to capture images of five coffee fields lated well with the percentage of ripe fruits ob-
obtained by Unmanned Aerial Vehicles (UAV). with distinct characteristics. served in the field (R² = 0.81).
[64] The study describes a method to classify coffee The model uses high-frequency vibrations, and The article evidenced an alternative for classifying
fruits according to their ripening stage: Unripe, electrical impedance measurements were planned coffee fruit differently from traditional operations.
Semiripe, Ripe-Overripe. to be conducted and correlated with the ripening
stage. The model used a Naive Bayes classifier.
[65] The study presents a dataset for classifying coffee The dataset has 5,048 images in six classes: over- The best model was GoogLeNet, which had a pre-
berries. ripe, immature, semi-mature, mature, small, and cision of better than 96.9%.
elephant. It was tested on the CNN GoogLeNet
and ShuffleNet.
Preprints.org (www.preprints.org) | NOT PEER-REVIEWED | Posted: 21 June 2024 doi:10.20944/preprints202406.1462.v1

17 of 34

CNN networks are used to classify the ripening stage of coffee beans by [60,62,65]. The paper’s
authors [60] classified coffee cherry fruit into immature, semi-mature, mature, overripe, and dry. [61]
classified coffee cherries based on skin color and shape characteristics. [63] classified coffee cherries
based on spectral and textural characteristics.
The networks tested to identify coffee maturity were DenseNet201, KNN, ResNet50, Naive Bayes,
and GoogLeNet. VGG16, VGG19, InceptionResNet-V2, Inception-v3, ANN, Deep-CNN, ShuffleNet
were also tested, but did not achieve satisfactory results when compared with other networks. It is not
possible to say which network presents the best performance among all the works analyzed because
the databases tested were different. The researches differ in the maturity levels they seek to classify
and consequently in the number of classes presented in each model. The studies studied used datasets
from 600 images to around 5,000 images. The size of the dataset also influences the model result.

4.5. Coffee Disease Classification

Several diseases affect coffee farming. These diseases cause serious damage and reduce or nullify
coffee productivity when poorly controlled. Studies on many coffee classifications aim to accurately
and quickly identify diseases in coffee leaves for effective management and control.
As illustrated in Tables 8, 9, 10, and 11, the first column corresponds to the literature review’s
reference; the second column describes the paper’s main objectives; the third column lists the models
and algorithms used in the paper; and the last column informs the results achieved.
Preprints.org (www.preprints.org) | NOT PEER-REVIEWED | Posted: 21 June 2024 doi:10.20944/preprints202406.1462.v1

18 of 34

Table 8. Coffee Disease Classification.

Reference Objectives and Scenario of Application Methodology Results

[66] The study presented an approach for classifying The model extracts low-level features in coffee The model achieved an accuracy of over 93.8%.
disease severity in coffee leaves. leaves, such as color, to reduce memory and com-
putational cost.
[67] The study addresses the detection of rust in coffee The proposed method is based on a CNN and uses The best model was SVM, which achieved an accu-
leaves. the transfer learning technique. racy of 96%.
[68] The study proposes applying methods to classify 4 The method used 3 configurations of the VGG16 VGG16 model achieved 100% accuracy with set-
diseases in Barako coffee: spots, insect infestation, model to classify a dataset of 3,958 coffee leaf im- ting: 100 epochs, 512 neurons, 0.5 dropouts, 0.0001
rust, and health. ages. learning rate, adam, and 32 batch size.
[69] The study identified and categorized coffee leaf Resnet50 and Mobilenet models were used, and a Resnet50 model presented the best performance
diseases: rust, wilt, and brown eye. dataset of 1,120 images of coffee leaves with 3,360 with 99.89% accuracy while MobileNet presented
images after data augmentation techniques. 97.01%.
[70] The study describes a method for finding regions The model uses a Deep Belief Network and a The proposed model achieved an accuracy of
damaged by coffee rust. dataset of 624 images of coffee leaves. 99.75%.
[71] The article proposed a model for detecting the rate The model applies three deep learning algorithms: The best model was modified BPNN, which
of coffee rust infection. Backpropagation Neural Network (BPNN), CNN, achieved a minimum MAE of 1,2462.
and Recurrent Neural Network (RNN).
[72] The study identifies diseases in Arabica coffee The proposed model was trained using max pool- The proposed model achieved an accuracy of
leaves such as Healthy, Miner, Rust, Phoma, and ing, dropout layer, two dense layers, and Adam 99.84% for 5 classes.
Cescospora. optimizer.
[73] The study presents a method to detect Coffee Leaf The model was based on CNN with few layers. The proposed model achieved an accuracy of 95%.
Rust.
[74] The study implements a model to identify biotic The model used YOLOv3 and the MobileNetV2 The model achieved an accuracy of 90%.
agents present in Robusta coffee leaves. algorithm.
[75] The study presents a method for detecting white The model used YOLOv5 and a dataset of 492 im- The model achieved a precision of 89.7%.
stem borer disease in coffee plants using an au- ages after data augmentation.
tonomous multi-terrain robot.
[76] The study presents a methodology to detect Coffee The model used twenty-five CNNs. The ResNet101V2 model achieved the highest test
Leaf Rust disease. with an accuracy of 95.56%.
[77] The study presents a hybrid approach to identify The proposed method uses MobileNetV3, Swin The hybrid proposed model achieved an accuracy
various diseases in coffee leaves, including Red Transformer, and variational autoencoder (VAE). of 84.29%.
Spider Mite and Rust. The model used the Robusta Coffee Leaf (RoCoLe)
dataset.
Preprints.org (www.preprints.org) | NOT PEER-REVIEWED | Posted: 21 June 2024 doi:10.20944/preprints202406.1462.v1

19 of 34

Table 9. Coffee Disease Classification.

Reference Objectives and Scenario of Application Methodology Results

[78] The study proposed a model for detecting diseases The study proposed two CNN models: the detec- The proposed model achieved an overall accuracy
and pests in coffee leaves in Panama. Classified dis- tion of coffee leaves and the detection of coffee leaf of 90%.
eases include Cercospora, Rust, Miner, and Phoma. diseases.
[79] The study presents a smartphone application clas- The model used MobileNet on a low-cost micro- The embedded cascade model presented an accu-
sifier of coffee leaf diseases, containing the classes controller board in two architectures (cascaded and racy of around 90%.
healthy, Rust, Sooty Molds, Cercospora, Phoma, single-stage). Two datasets were used: BRACOL
and Leaf Miner. (1,747 samples) and LiCoLe (4,667 samples).
[80] The study presents a few-shot learning model to The proposed model used two models, Triplet- The best result was using the Symptoms Dataset
classify and estimate the severity of biotic stresses Net and ProtoNet. Two datasets were used: the for biotic stress classification, which achieved an
on coffee leaves such as Rust, Miner, Brown Leaf Leaf Dataset with 1,685 images and the Symptoms accuracy of 96.72%. The severity estimation task
Spot, and Cercospora. Dataset with 2,722 images. achieved an accuracy of 93.25%.
[81] The study presents a method for detecting healthy An algorithm was developed by modifying VGG16 The proposed model achieved an accuracy of
and diseased coffee leaves. architecture. A dataset was collected with 4,000 97.9%.
images.
[82] The study presents a dataset of images of Peruvian The dataset contains 1,006 leaf images divided The proposed model achieved an accuracy of
coffee leaves, called CoLeaf, with 10 different nutri- into three subsets: Catimor, Caturra, and Borbon. 87.75%.
tional deficiencies. ResNet50 network was used for classification.
[83] The study presents a method for detecting cof- The model consists of two algorithms, GoogLeNet The model achieved an accuracy of 99.08%.
fee diseases: Wilt, Rust, Cercospora, Sooty Moldy, and RESNET, to extract high-level features. MLP
Phoma, and Phoma Costaricensis. was used to classify coffee leaf and berry diseases.
A dataset of 3,288 images was used.
[84] The study describes an app to identify diseases and The CNN model used two datasets, Segmentation For semantic segmentation, the UNet model pre-
pests of coffee leaves: Miner, Rust, Brown leaf spot, Dataset and Symptoms Dataset, and two architec- sented the best performance with 99.53% accu-
Cercospora, and Healthy. tures, UNet and PSPNet. racy. The best result for the symptom classification
was achieved with ResNet50 with an accuracy of
97.07%.
[85] The study describes a dataset of images of Ara- The dataset is called JMuBEN and JMuBEN2 and The dataset can evaluate ML models for coffee dis-
bica coffee leaves, which have five classes: Rust, contains 58,555 images. ease classification.
Cescospora, Phoma, Miner, and Healthy.
Preprints.org (www.preprints.org) | NOT PEER-REVIEWED | Posted: 21 June 2024 doi:10.20944/preprints202406.1462.v1

20 of 34

Table 10. Coffee Disease Classification.

Reference Objectives and Scenario of Application Methodology Results

[86] The study presents a method to recognize Cer- Two models were created. The first used a modi- Using the texture model, the kappa rate was 0.900,
cospora, Rust, and Healthy coffee leaves based on fication of AlexNet, and the second used a texture and the sensitivity was 0.933. Using DLDR, the best
Deep Learning and texture attributes attribute extraction as input to the ANN classifier. result for Kappa was 0.970, and the sensitivity was
A dataset of about 500 images for each class was 0.980.
used after augmentation.
[87] The study presents a model to identify diseases and The Mask R-CNN was used for instance segmen- The model achieved an average precision AP of
pests in coffee leaves based on field images. tation. For semantic segmentation, two networks 73.90% for instance segmentation and AP of 71.90%
were used: UNet and PSPNet. BRACOT and BRA- for object detection.
COL datasets were used.
[88] The study presents a model to identify and estimate The model used different CNN architectures: The best model achieved an accuracy of 95.24%
the stress severity caused by biotic agents on coffee AlexNet, GoogLeNet, VGG16, ResNet50, and Mo- for the biotic stress classification and 86.51% for
leaves: Leaf Miner, Rust, Brown Leaf Spot, and bileNetV2. A dataset BRACOL was used. severity estimation.
Cercospora Leaf Spot.
[89] The study aims to predict the incidence of Phoma The model was tested with KNN, MLP, SVN, RF, The best model was XGBoost, with a Root Mean
leaf spot disease in coffee plantations considering Extreme Gradient Boosting (XGBoost), and Gradi- Square Error (RMSE) of 3.45% for the high-yielding
the climatic variables in the coffee-producing re- ent Boosting (GradBOOSTING) algorithms. trees.
gions of Brazil.
[90] The study aims to predict the incidence of Rust, The model was tested with Multiple Linear Regres- The best model was RFT, with RMSE values rang-
Cercospora, Miner, and Coffee Borer in coffee plan- sion (RLM), KNN, Random Forest Regressor (RFT), ing from 0.227 to 0.853 for high yield.
tations considering the climatic variables in the and MLP.
coffee-producing regions of Brazil.
[91] The study classifies healthy and unhealthy coffee The paper presents a model that uses the Restricted GWO achieved an accuracy of 98%.
cherries in various stages of maturity. Boltzmann Machine Algorithm with Grey Wolves
Optimization (GWO). A dataset with 475 coffee
cherries.
[92] The study presents a method to detect the presence The study trained two neural network architec- The neural network trained with NVIDIA achieved
of Coffee Rust. tures: with OpenCV and with NVIDIA Digits. the best performance with an accuracy of 98%.
[93] The study presents a method to classify the biotic The study presents three CNN-based methods: The HLGCM achieved the best performance with
stress on coffee leaves. ECNN, HLGGM, and HLGCM. A combination of an accuracy of 99.49%.
datasets was used: Bracol, JMUBEN, and PDCMD.
[94] The study presents a dataset with robusta coffee RoCoLe has 1,560 coffee leaf images with six classes: RoCoLe can be used to train and validate the per-
leaf images called RoCoLe. healthy, Red Spider Mite, Rust level 1, Rust level 2, formance of ML algorithms.
Rust level 3, and Rust level 4.
[95] The study identifies and categorizes Cucurbit leaf The model used federated learning with CNN and The proposed model achieved an average accuracy
diseases in four severity levels. DT. A dataset with 4,585 images was used with 14 of 89.54%.
classes.
Preprints.org (www.preprints.org) | NOT PEER-REVIEWED | Posted: 21 June 2024 doi:10.20944/preprints202406.1462.v1

21 of 34

Table 11. Coffee Disease Classification.

Reference Objectives and Scenario of Application Methodology Results

[96] The study detects four classes of the severity of Cof- The paper compares different decision tree models. The best model was the Logistic Model Tree (LTM),
fee Leave Rust vegetation indices extracted from which achieved a precision of 0.672.
UAV imagery.
[97] The study detects contamination by Aspergillus The model used 6 ML algorithms: linear discrimi- The proposed model achieved an accuracy of
ochraceous in Robusta green coffee beans. nant analysis (LDA), SVM, KNN, DT, Naive Bayes 97.5%.
(NB), and quadratic discriminant analysis (QDA).
[98] The study classifies coffee plant diseases as The paper compares DenseNet121 with Enhanced The best model was Enhanced EfficientNetV2-S
Cescospora, Miner, Phoma, Rust, and Healthy. EfficientNetV2-5. The Kaggle coffee plant dataset with an accuracy of 98.1%.
and the JMuBEN Mendeley dataset were used with
5000 images.
[99] The study classifies coffee plant diseases as The model used a Simple Linear Iterative Clus- The proposed model achieved an accuracy of 99.17
Cescospora, Miner, Phoma, and Rust. tering (SLIC) segmentation algorithm and the %.
Densenet-264. The JMuBEN Mendeley and Kaggle
coffee plant datasets were used with 7,044 images.
[100] The proposed model achieved Kappa coefficient of
0.96 for N and P deficiency, and 0.92 for B.
Preprints.org (www.preprints.org) | NOT PEER-REVIEWED | Posted: 21 June 2024 doi:10.20944/preprints202406.1462.v1

22 of 34

The white stem borer disease is a major pest of Arabica [75,101] proposed a method to identify
them. The beetle pierces the coffee stem and remains buried until the plant falls completely. As the
disease is difficult to diagnose in the early stages of its infestation, it causes major problems for coffee
producers. The authors of the paper [75] used the YoloV5 deep learning model to identify white stem
borer disease using color, texture, and shape characteristics. The Jackal UGV robot navigated and
mapped the simulated environment of an Arabica coffee plantation using a depth camera and state
and location estimation algorithms.
Coffee Leaf Rust is a serious disease that affects many coffee-producing regions. It is caused by
a pathogenic fungus that attacks the underside of coffee leaves and is described by yellow-orange,
powdery dots. If left untreated, rust can cause a drop in coffee production. [76] carried out a
comparative study designed to identify Coffee Leaf Rust with twenty-five models and achieved
the best performance of 90% with models ResNet101V2, InceptionV3, ResNet50V2, Xception, and
DenseNet169. [67] used a CNN architecture to spot rust infestation and identify rust in coffee leaves of
different varieties and stages of development.
The paper [84] presented an application for identifying and quantifying diseases and pests in
coffee leaves using smartphone images. The application consists of two main modules: semantic
segmentation for severity and symptom classification.
The authors of the paper [66] proposed a method to capture the discolored distribution of coffee
leaves, allowing her to identify the severity of the disease more easily.
In [68], the authors achieved 100% accuracy in identifying disease with no errors using VGG16
architecture, hence demonstrating that the appropriate configuration and optimization can generate
efficient results. [81] also used VGG16 to classify diseases in coffee leaves. In this paper, the authors
modified VGG16 and achieved an accuracy of 97.9% to classify healthy and infected coffee leaves.
The work in [77] proposed a hybrid feature fusion with MobileNetV3 that extracts local features,
while Swin Transformer extracts high-level features classification performance and rust. [78] used
two models. The first model identifies coffee leaves. This model used a CNN architecture with 10
convolutional layers, Adam optimization, softmax, and 100 epochs and achieved an accuracy of 95%.
The second model was used to detect diseases from coffee leaves, and the CNN architecture has 20
convolutional layers, Adamax optimization, and 100 epochs, achieving an accuracy of 90%. In the
same way, [79] proposed two architectures to classify diseases of coffee leaves. The first identifies
the diseases of coffee in six classes. The second architecture is used to improve the classification
performance made by the first stage.
On the other hand, [87] proposed three experiments that can learn to classify using just a few
examples. Each experiment was tested with two architectures: Tripletnet and Protonet. The first two
experiments were tested to classify the biotic stress of coffee leaves. The third experiment sought to
automatically estimate the severity of the disease: low, very low, high, very high.
The paper [82] introduced a dataset with images captured in a controlled environment showing
nutritional deficiencies in coffee leaves. The nutritional deficiencies are Nitrogen, Phosphorus, Potas-
sium, Magnesium, Boron, Manganese, Calcium, and Iron. The nutritional deficiencies are detected and
classified by analyzing the color and shape characteristics. Leaves with more than one deficiency can
also be detected.
Moreover, [83] proposed a model with GoogLeNet and RestNet in the feature extraction phase
and MLP with traditional ML classifiers such as KNN, DT, SVM, and RF for classification tasks.
Three CNN-based methods were proposed in [93]. ECNN focuses on the effective concatenation of
five CNNs; HLGGM combines dimension-reduced Mobile-Net v3 features with handcrafted features;
and HLGCM has reduced dimensionality and uses a DT.
The networks tested to identify coffee diseases were SVM, VGG16, ResNet50, Deep Belief Net-
work, BPNN, MobileNetV2, ResNet101V2, TripletNet, ProtoNet, GooLeNet, ResNet, UNet, AlexNet,
ANN, Mask R-CNN, XGBoost, RFT, NVIDIA Digits, Decision Tree, Enhanced EfficientNetV2-5, and
DenseNet264. MobileNet, MobileNetV3, RNN, CNN, Swin Transformer, PSPNet, KNN, MLP, Grad-
Preprints.org (www.preprints.org) | NOT PEER-REVIEWED | Posted: 21 June 2024 doi:10.20944/preprints202406.1462.v1

23 of 34

Boosting, RLM, OpenCV, LDA, NB, QDA, DenseNet121, were also tested, but did not achieve satisfac-
tory results when compared with other networks. It is not possible to say which network presents
the best performance among all the works analyzed because the databases tested were different. The
works differ in the diseases they seek to classify and consequently in the number of classes presented
in each model. The studies studied used datasets from 400 images to around 58,000 images. The size
of the dataset also influences the model result.
The proposed methodologies for classifying coffee diseases can be applied to assist farmers in
early detection and making decisions to protect coffee plantations. It is necessary to include more
classifications for coffee diseases and expand the size of the dataset. Future studies can also compare
other deep learning algorithms with other pre-trained models to achieve higher accuracy.

5. Challenges and Future Trends

ML, along with complementary technologies, such as Computer Vision, are revolutionizing coffee
farming, propelling agribusiness towards unprecedented efficiency, speed, and precision in decision-
making while reducing operational costs. Our review evidenced the existence of several computational
models devised for coffee bean classification, addressing various attributes such as defects, roasting,
diseases, aroma and flavor, and maturation of coffee, hence demonstrating the potential for continuous
advancements. However, despite this progress, most of the existing AI-based models and tools
predominantly reside in experimental phases, lacking widespread practical deployment.
They further often exhibit a restricted focus, tailored to particular regions [82,89] or coffee types
[35,45,54,64,68,74,85,90,94,97] and further demonstrate a limited scope in identifying nuanced charac-
teristics like roast degrees [47] and maturity stages [60,61]. The need for more universally applicable
models is evident, especially in areas like aromatic profiling, where ML remains underutilized, reveal-
ing significant untapped potential for research and industry applications.
Furthermore, the scarcity of extensive image datasets is a critical bottleneck, underscoring the
necessity for enriched coffee bean data to enable robust model generalization across diverse environ-
mental and cultural contexts. Tables 12, 13 and 14 provide a concise summary of the datasets used in
the analyzed articles and are available for download. Additionally, the Tables list datasets that could
be valuable for future coffee classification tasks using ML.
Preprints.org (www.preprints.org) | NOT PEER-REVIEWED | Posted: 21 June 2024 doi:10.20944/preprints202406.1462.v1

24 of 34

Table 12. Summary Datasets.

Reference Number of Im- Number of Categories Types Download Link

ages
[29] 8,000 4 (peaberry, long berry, pre- Single bean https://comvis.unsyiah.ac.id/usk-coffee/
mium, defect.)
[31] 1,813 2 (defective and normal) Single bean https://github.com/Tauranis/deep_coffee/
[36] 4,617 3 (good and bad - insect bite Single bean https://github.com/tanius/smallopticalsorter/tree/
and broken) master/classifier-trainingdata
[37] 1554 3 (espresso, Kenya and Star- Single bean https://muratkoklu.com/dataset/Coffee_Image_
bucks pike place) Dataset.zip
[57] 56 .csv archive https://github.com/Javiersuing/GitHub/blob/master/
AlmacafeDataBase_CrossV_v4.ipynb
[68] 3958 4 (Healthy, Rusted, Infested, Leaves https://github.com/francismontalbo/swatdcnn/tree/
and Spotted Barako) main
[79] 6000 6 (Healthy, Rust, Sooty Leaves Licole F.J.P. Montalbo, A.A. Hernandez, Classifying Barako
Molds, Cercospora, Phoma coffee leaf diseases using deep convolutional models
and Leaf Miner) (2020).
[82] 1006 10 (Boron, Iron, Potassium, Leaves CoLeaf https://data.mendeley.com/datasets/brfgw4
Calcium, Magnesium, Man- 6wzb/1
ganese, Nitrogen, Phospho-
rus, calcium and healthy)
[80], 142 6 (Leaf Miner, Cercospora Leaves BARBEDO, Jayme Garcia Arnal. Plant disease identifica-
[84] Leaf Spot, Rust, Bacterial tion from individual lesions and spots using deep learning.
Blight, Blister Spot, Brown Biosystems Engineering, v. 180, p. 96-107, 2019.
Leaf Spot)
[85] 58,555 5 (Phoma, Cerscospora, Rust, Leaves JMuBEN2
Healthy, and Miner) https://data.mendeley.com/datasets/tgv3zb82nd/1
[87] 300 5 (Leaf Miner, Rust, Brown Leaves BRACOT - A Brazilian Arabica Coffee Tree images dataset,
Leaf Spot, and Cercospora for instance segmentation of coffee leaves
Leaf Spot) https://data.mendeley.com/datasets/pmkbyjpf6k/1
Preprints.org (www.preprints.org) | NOT PEER-REVIEWED | Posted: 21 June 2024 doi:10.20944/preprints202406.1462.v1

25 of 34

Table 13. Summary Datasets.

Reference Number of Im- Number of Categories Types Download Link

ages
[66], 1747 4 (Leaf Miner, Leaf Rust, Leaves BRACOL - A Brazilian Arabica Coffee Leaf images dataset
[79], Brown Leaf Spot, and Cer- to identification and quantification of coffee diseases and
[80], cospora Leaf Spot) pests https://data.mendeley.com/datasets/yy2k5y8mxg/
[84], 1
[87],
[88],
[93]
[66], 1,560 6 (Healthy, Red Spider Mite Leaves RoCoLe: A dataset with robusta coffee leaf images
[77], Presence, Rust level 1, Rust https://data.mendeley.com/datasets/c5yvn32dzg/2
[94] level 2, Rust level 3 and Rust
level 4)
[93], 22,591 3 (Coffee Rust, Cescospora Leaves JMuBEN
[98], and Phoma) https://data.mendeley.com/datasets/t2r6rszp5c/1
[99]
[93], 76,000 (for cof- 88 classes, for the coffee Leaves Kaggle Plant Disease Classification Merged Dataset
[99] fee disease are disease are 4 classes (Cer- https://www.kaggle.com/datasets/alinedobrovsky/
1,103 images) cospora, Healthy, Red Spider plant-disease-classification-merged-dataset
Mite and Rust)
Preprints.org (www.preprints.org) | NOT PEER-REVIEWED | Posted: 21 June 2024 doi:10.20944/preprints202406.1462.v1

26 of 34

Table 14. Summary Datasets.

Reference Number of Im- Number of Categories Types Download Link

ages
– 2,000 2 (good and bad) Single bean https://github.com/tanius/smallopticalsorter/tree/
master/classifier-trainingdata
– 1,600 4 (Dark, green, light and Single bean https://www.kaggle.com/datasets/gpiosenka/coffee-
medium) bean-dataset-resized-224-x-224
– 542 2(Miner and Rust) Leaves https://www.kaggle.com/datasets/alvarole/coffee-
leaves-disease
– 1,000 3 (Healthy, Red Spider Mite Leaves https://www.kaggle.com/datasets/coffeedisease/
and Rust) coffee-plant-disease
– 1,664 4 (Miner, Nodisease, Phoma Leaves https://www.kaggle.com/datasets/gauravduttakiit/
and Rust) coffee-leaf-diseases https://www.kaggle.com/datasets/
stunningvisionai/coffee-leaf-diseases-yolo https://www.
kaggle.com/datasets/badasstechie/coffee-leaf-diseases
– 600 1 (green coffee beans) Multiple https://www.kaggle.com/datasets/danielmejiar/green-
beans coffee-beans
– 1,800 3 (Cercospora, Healthy and Leaves https://www.kaggle.com/datasets/
Rust) miladatulmuharromah/coffee-leaves-disease
– 6,000 4 (Dark, green, light, and Multiple https://www.kaggle.com/datasets/dewanakretarta/
medium) beans resize-224x224-coffee-bean-dataset-v2
– 175 3 (half ripe, ripe, unripe) Multiple cher- https://www.kaggle.com/datasets/
ries maulanaimanpratama/coffee-fruit-images
– – Is a merge of BrACoL , – CoffeeNet
JMuBEN, JMuBEN2 , RoCoL https://drive.google.com/drive/folders/1dDEw-
, and LiCoLe VhuGx37wSVqhYQ-m1zKFug2SpDz
Preprints.org (www.preprints.org) | NOT PEER-REVIEWED | Posted: 21 June 2024 doi:10.20944/preprints202406.1462.v1

27 of 34

Although little explored, agribusiness professionals should prepare themselves for the future tools
that will emerge from the research results presented in this article. These agribusiness professionals
will encounter new challenges and changes in the way they work. They must adapt and relearn their
roles, focusing on their analytical skills in data-driven agriculture.
Recognizing the urgent demand for refined classification tools to aid coffee growers, this work
underscores the importance of machine learning-based image classification in supporting decision-
making and enhancing overall industry efficiency.
Finally, the transformative power of ML and Computer Vision offers promising prospects for
coffee bean diagnostics, promising to enhance productivity and management confidence significantly.
Future research should, therefore, expand upon these findings, focusing on refining classification
techniques for a broader and more accurate application in coffee bean classification.
As a result, Figure 7 lists the roadmap of future trends for resources in ML coffee classification. To
maximize production, reduce costs, and increase precision in decision-making in coffee farming, future
research needs to increase the capacity to implement higher-performance ML algorithms, increase the
size of image datasets, and, finally, develop fewer generalist methods and more classes considered.

• Maximize production;
• Reduce costs;
• Increase precision in decision

• Capacity to implement higher • Large-scale • Less generalist methods;

performance Machine Learning images datasets • More classes considered
Algorithms.
Figure 7. Roadmap of future trends for resource in Machine Learning coffee classification

6. Conclusions
This comprehensive literature review examined the application of ML techniques to coffee bean
and leaves classification, focusing on the last five years of research related to coffee defects, roasting,
maturity, sensing, and diseases.
The synthesis of data extracted from the reviewed works offers valuable insights, presenting a
comprehensive overview of contemporary day research, the most frequently used algorithms, and
model comparisons.
Some of the research directions for the future include creating new data sets that are larger, less
general, and with more classes, and, above all, the search for increasing the capacity to implement
higher-performance ML algorithms.
Notably, there has been a significant increase in relevant scientific publications, reflecting the
growing impact of machine learning-based image classification in advancing coffee agriculture. This
surge in scholarly activity has catalyzed increased investments in developing new products and
services, underscoring the promising trajectory for future ML research within the coffee domain.
Author Contributions: I.V.C.M. contributed to this study’s conceptualization, data curation, resources, writing,
review, and editing. F.A.P.F., N.V., and H.P. contributed to methodology, supervision, review, validation, and
funding. All authors read and approved the final manuscript.
Preprints.org (www.preprints.org) | NOT PEER-REVIEWED | Posted: 21 June 2024 doi:10.20944/preprints202406.1462.v1

28 of 34

Funding: This work was partially funded by CNPq (Grant Nos. 403612/2020-9, 311470/2021-1 and 403827/2021-
3), by Sao Paulo Research Foundation (FAPESP) (Grant No. 2021/06946-0), by Minas Gerais Research Foundation
(FAPEMIG) (Grant No. APQ-00810-21, PPE-00124-23) and by the project "Resource-aware Machine Learning
Model Optimization for Edge Computing" supported by xGMobile - EMBRAPII-Inatel Competence Center on
5G and 6G Networks, with financial resources from the PPI IoT/Manufatura 4.0 from MCTI grant number
052/2023, signed with EMBRAPII and by the French National Research Agency (ANR) in the framework of the
Investissements d’avenir program (ANR-10-AIRT-05 and ANR-15-IDEX-02) and the MIAI @ Grenoble Alpes
(ANR-19-P3IA-0003).
Data Availability Statement: Data declarations do not apply to this paper.
Conflicts of Interest: The authors declare that they have no competing interests.

References
1. Gois, T.C.; Thomé, K.M.; Balogh, J.M. Behind a cup of coffee: International market structure and competi-
tiveness. Competitiveness Review: An International Business Journal 2023, 33, 993–1009. https://doi.org/10.110
8/CR-10-2021-0141.
2. Bosso, H.; Barbalho, S.M.; de Alvares Goulart, R.; Otoboni, A.M.M.B. Green coffee: economic relevance
and a systematic review of the effects on human health. Critical Reviews in Food Science and Nutrition 2023,
63, 394–410. https://doi.org/10.1080/10408398.2021.1948817.
3. Dhanya, V.; Subeesh, A.; Kushwaha, N.; Vishwakarma, D.K.; Kumar, T.N.; Ritika, G.; Singh, A. Deep learning
based computer vision approaches for smart agricultural applications. Artificial Intelligence in Agriculture
2022. https://doi.org/10.1016/j.aiia.2022.09.007.
4. Elbasi, E.; Mostafa, N.; AlArnaout, Z.; Zreikat, A.I.; Cina, E.; Varghese, G.; Shdefat, A.; Topcu, A.E.; Abdelbaki,
W.; Mathew, S.; others. Artificial intelligence technology in the agricultural sector: a systematic literature
review. Ieee Access 2022, 11, 171–202. https://doi.org/10.1109/ACCESS.2022.3232485.
5. Pragathi, S.; Jacob, L. Review On Image based Coffee Bean Quality Classification: Machine Learning
Approach. 2022 4th International Conference on Advances in Computing, Communication Control and
Networking (ICAC3N). IEEE, 2022, pp. 706–711. https://doi.org/10.1109/ICAC3N56670.2022.10074124.
6. Sarkar, C.; Gupta, D.; Gupta, U.; Hazarika, B.B. Leaf disease detection using machine learning and deep
learning: Review and challenges. Applied Soft Computing 2023, p. 110534. https://doi.org/10.1016/j.asoc.20
23.110534.
7. Sunil, C.; Jaidhar, C.; Patil, N. Systematic study on deep learning-based plant disease detection or classifica-
tion. Artificial Intelligence Review 2023, pp. 1–98. https://doi.org/10.1007/s10462-023-10517-0.
8. Sajitha, P.; Andrushia, A.D.; Anand, N.; Naser, M. A Review on Machine Learning and Deep Learning
Image-based Plant Disease Classification for Industrial Farming Systems. Journal of Industrial Information
Integration 2024, p. 100572. https://doi.org/10.1016/j.jii.2024.100572.
9. Anto, I.A.F.; Munandar, A.; Wibowo, J.W.; Salim, T.I.; Mahendra, O. Coffee Bean Roasting Levels Detection:
A Systematic Review. 2023 IEEE 7th International Conference on Information Technology, Information
Systems and Electrical Engineering (ICITISEE). IEEE, 2023, pp. 146–151. https://doi.org/10.1109/ICITISEE5
8992.2023.10404775.
10. Sharma, K.; Sharma, C.; Sharma, S.; Asenso, E. Broadening the research pathways in smart agriculture:
predictive analysis using semiautomatic information modeling. Journal of Sensors 2022, 2022, 1–19. https:
//doi.org/10.1155/2022/5442865.
11. Sharma, S.; Sharma, C.; Asenso, E.; Sharma, K.; others. Research Constituents and Trends in Smart
Farming: An Analytical Retrospection from the Lens of Text Mining. Journal of Sensors 2023, 2023. https:
//doi.org/10.1155/2023/6916213.
12. Sharma, K.; Sethi, G.K.; Bawa, R.K. A comparative analysis of deep learning and deep transfer learning
approaches for identification of rice varieties. Multimedia Tools and Applications 2024, pp. 1–18. https:
//doi.org/10.1007/s11042-024-19126-7.
13. Komal.; Sethi, G.K.; Bawa, R.K. Automatic Rice Variety Identification System: state-of-the-art review,
issues, challenges and future directions. Multimedia Tools and Applications 2023, 82, 27305–27336. https:
//doi.org/10.1007/s11042-023-14487-x.
14. Komal.; Sethi, G.K.; Bawa, R.K. A prototype of automatic rice variety identification system using artificial
intelligence techniques. AIP Conference Proceedings 2022, 2455, 040004.
Preprints.org (www.preprints.org) | NOT PEER-REVIEWED | Posted: 21 June 2024 doi:10.20944/preprints202406.1462.v1

29 of 34

15. Sethi, G.; Bawa, R.; others. A Hybrid Approach of Preprocessing and Segmentation Techniques in Automatic
Rice Variety Identification System. Journal of Scientific Research 2022, 14. https://doi.org/10.3329/jsr.v14i1.5
4811.
16. Javanmardi, S.; Ashtiani, S.H.M.; Verbeek, F.J.; Martynenko, A. Computer-vision classification of corn seed
varieties using deep convolutional neural network. Journal of Stored Products Research 2021, 92, 101800.
https://doi.org/10.1016/j.jspr.2021.101800.
17. Hu, R.; Zhang, S.; Wang, P.; Xu, G.; Wang, D.; Qian, Y. The identification of corn leaf diseases based on
transfer learning and data augmentation. Proceedings of the 3rd International Conference on Computer
Science and Software Engineering, 2020, pp. 58–65. https://doi.org/10.6041/j.issn.1000-1298.2020.02.025.
18. de Medeiros, A.D.; Capobiango, N.P.; da Silva, J.M.; da Silva, L.J.; da Silva, C.B.; dos Santos Dias, D.C.F.
Interactive machine learning for soybean seed and seedling quality classification. Scientific reports 2020,
10, 11267. https://doi.org/10.1038/s41598-020-68273-y.
19. Janiesch, C.; Zschech, P.; Heinrich, K. Machine learning and deep learning. Electronic Markets 2021,
31, 685–695. https://doi.org/10.1007/s12525-021-00475-2.
20. Russell, S.J.; Norvig, P. Artificial intelligence: A modern approach, 4 ed.; Pearson, 2021.
21. Mahadevkar, S.V.; Khemani, B.; Patil, S.; Kotecha, K.; Vora, D.R.; Abraham, A.; Gabralla, L.A. A review on
machine learning styles in computer vision—techniques and future directions. Ieee Access 2022, 10, 107293–
107329.
22. Han, K.; Wang, Y.; Chen, H.; Chen, X.; Guo, J.; Liu, Z.; Tang, Y.; Xiao, A.; Xu, C.; Xu, Y.; others. A
survey on vision transformer. IEEE transactions on pattern analysis and machine intelligence 2022, 45, 87–110.
https://doi.org/10.1109/TPAMI.2022.3152247.
23. Dosovitskiy, A.; Beyer, L.; Kolesnikov, A.; Weissenborn, D.; Zhai, X.; Unterthiner, T.; Dehghani, M.; Minderer,
M.; Heigold, G.; Gelly, S.; others. An image is worth 16x16 words: Transformers for image recognition at
scale. arXiv preprint arXiv:2010.11929 2020.
24. Uddin, M.S.; Bansal, J.C. Computer Vision and Machine Learning in Agriculture, Volume 2; 2022; pp. 1–8.
25. Micaraseth, T.; Pornpipatsakul, K.; Chancharoen, R.; Phanomchoeng, G. Coffee Bean Inspection Machine
with Deep Learning Classification. 2022 International Conference on Electrical, Computer, Communications
and Mechatronics Engineering (ICECCME). IEEE, 2022, pp. 1–5. https://doi.org/10.1109/ICECCME55909
.2022.9987835.
26. Liang, C.S.; Xu, Z.Y.; Zhou, J.Y.; Yang, C.M.; Chen, J.Y. Automated Detection of Coffee Bean Defects using
Multi-Deep Learning Models. 2023 VTS Asia Pacific Wireless Communications Symposium (APWCS). IEEE,
2023, pp. 1–5. https://doi.org/10.1109/APWCS60142.2023.10234059.
27. Septiarini, A.; Hamdani, H.; Burhandenny, A.E.; Nur, S.; Winarno, E. The color-texture features and machine
learning approach for quality detection of coffee beans. 2023 9th International Conference on Computer and
Communication Engineering (ICCCE). IEEE, 2023, pp. 217–222. https://doi.org/10.1109/ICCCE58854.2023.
10246091.
28. Kuo, C.J.; Chen, C.C.; Chen, T.T.; Tsai, Z.; Hung, M.H.; Lin, Y.C.; Chen, Y.C.; Wang, D.C.; Homg, G.J.; Su,
W.T. A labor-efficient gan-based model generation scheme for deep-learning defect inspection among dense
beans in coffee industry. 2019 IEEE 15th International Conference on Automation Science and Engineering
(CASE). IEEE, 2019, pp. 263–270. https://doi.org/10.1109/COASE.2019.8843259.
29. Febriana, A.; Muchtar, K.; Dawood, R.; Lin, C.Y. USK-COFFEE Dataset: A Multi-class Green Arabica Coffee
Bean Dataset for Deep Learning. 2022 IEEE International Conference on Cybernetics and Computational
Intelligence (CyberneticsCom). IEEE, 2022, pp. 469–473. https://doi.org/10.1109/CyberneticsCom55287.2
022.9865489.
30. Shao, B.; Hou, Y.; Huang, N.; Wang, W.; Lu, X.; Jing, Y. Deep Learning based Coffee Beans Quality
Screening. 2022 IEEE International Conference on e-Business Engineering (ICEBE). IEEE, 2022, pp. 271–275.
https://doi.org/10.1109/ICEBE55470.2022.00054.
31. Lee, J.Y.; Jeong, Y.S. Prediction of defect coffee beans using CNN. 2022 IEEE International Conference on Big
Data and Smart Computing (BigComp). IEEE, 2022, pp. 202–205. https://doi.org/10.1109/BigComp54360.2
022.00046.
32. Kuo, C.J.; Wang, D.C.; Chen, T.T.; Chou, Y.C.; Pai, M.Y.; Horng, G.J.; Hung, M.H.; Lin, Y.C.; Hsu, T.H.; Chen,
C.C. Improving defect inspection quality of deep-learning network in dense beans by using hough circle
Preprints.org (www.preprints.org) | NOT PEER-REVIEWED | Posted: 21 June 2024 doi:10.20944/preprints202406.1462.v1

30 of 34

transform for coffee industry. 2019 IEEE International Conference on Systems, Man and Cybernetics (SMC).
IEEE, 2019, pp. 798–805. https://doi.org/10.1109/SMC.2019.8914175.
33. Heryanto, T.A.; Nugraha, I.G.B.B. Classification of Coffee Beans Defect Using Mask Region-based Convolu-
tional Neural Network. 2022 International Conference on Information Technology Systems and Innovation
(ICITSI). IEEE, 2022, pp. 333–339. https://doi.org/10.1109/ICITSI56531.2022.9970890.
34. Chen, S.Y.; Chiu, M.F.; Zou, X.W. Real-time defect inspection of green coffee beans using NIR snapshot
hyperspectral imaging. Computers and Electronics in Agriculture 2022, 197, 106970. https://doi.org/10.1016/j.
compag.2022.106970.
35. Gomes, W.P.C.; Gonçalves, L.; da Silva, C.B.; Melchert, W.R. Application of multispectral imaging combined
with machine learning models to discriminate special and traditional green coffee. Computers and Electronics
in Agriculture 2022, 198, 107097. https://doi.org/10.1016/j.compag.2022.107097.
36. Chen, P.H.; Jhong, S.Y.; Hsia, C.H. Semi-supervised learning with attention-based CNN for classification of
coffee beans defect. 2022 IEEE International Conference on Consumer Electronics-Taiwan. IEEE, 2022, pp.
411–412. https://doi.org/10.1109/ICCE-Taiwan55306.2022.9869187.
37. Unal, Y.; Taspinar, Y.S.; Cinar, I.; Kursun, R.; Koklu, M. Application of pre-trained deep convolutional
neural networks for coffee beans species detection. Food Analytical Methods 2022, 15, 3232–3243. https:
//doi.org/10.1007/s12161-022-02362-8.
38. Putra, B.T.W.; Amirudin, R.; Marhaenanto, B. The evaluation of deep learning using convolutional neural
network (CNN) approach for identifying Arabica and Robusta coffee plants. Journal of Biosystems Engineering
2022, 47, 118–129. https://doi.org/10.1007/s42853-022-00136-y.
39. Wang, Y.F.; Cheng, C.C.; Tsai, J.K. Implementation of Green Coffee Bean Quality Classification Using
Slim-CNN in Edge Computing. 2022 IEEE 5th International Conference on Knowledge Innovation and
Invention (ICKII). IEEE, 2022, pp. 133–135. https://doi.org/10.1109/ICKII55100.2022.9983596.
40. Kesiman, M.W.A.; Sulaiman, I.; Maysanjaya, I.M.D.; Dermawan, K.T. Benchmarking A New Dataset for
Coffee Bean Defects Classification Based on SNI 01-2907-2008. 2023 International Conference on Information
Technology Research and Innovation (ICITRI). IEEE, 2023, pp. 75–80. https://doi.org/10.1109/ICITRI59340
.2023.10249345.
41. Tsai, J.J.; Chang, C.C.; Huang, D.Y.; Lin, T.S.; Chen, Y.C. Analysis and classification of coffee beans using
single coffee bean mass spectrometry with machine learning strategy. Food Chemistry 2023, 426, 136610.
https://doi.org/10.1016/j.foodchem.2023.136610.
42. Pratondo, A.; Zani, T.; Novianty, A.; Pudjoatmodjo, B. Raw Coffee Bean Classification for Roasting Suitability
Assessment Using Transfer Learning. 2023 IEEE 11th Conference on Systems, Process & Control (ICSPC),
2023, pp. 1–6. https://doi.org/10.1109/ICSPC59664.2023.10419990.
43. Hamdani, H.; Septiarini, A.; Akbar, F.; Saputra, R.; Nurmadewi, D.; Priyatna, S.E. Classification of Arabica
Coffee Beans Based on Multi-Features Using Artificial Neural Networks. 2023 1st International Conference
on Advanced Engineering and Technologies (ICONNIC), 2023, pp. 85–90. https://doi.org/10.1109/
ICONNIC59854.2023.10467549.
44. Agresti, P.D.M.; Franca, A.S.; Oliveira, L.S.; Augusti, R. Discrimination between defective and non-defective
Brazilian coffee beans by their volatile profile. Food chemistry 2008, 106, 787–796. https://doi.org/10.1016/j.
foodchem.2007.06.019.
45. Septiarini, A.; Hamdani, H.; Rifani, A.; Arifin, Z.; Hidayat, N.; Ismanto, H. Multi-Class Support Vector
Machine for Arabica Coffee Bean Roasting Grade Classification. 2022 5th International Conference on
Information and Communications Technology (ICOIACT). IEEE, 2022, pp. 407–411. https://doi.org/10.110
9/ICOIACT55506.2022.9971897.
46. Janandi, R.; Cenggoro, T.W. An Implementation of convolutional neural network for coffee beans quality
classification in a mobile information system. 2020 International Conference on Information Management
and Technology (ICIMTech). IEEE, 2020, pp. 218–222. https://doi.org/10.1109/ICIMTech50083.2020.921125
7.
47. Hakim, M.; Djatna, T.; Yuliasih, I. Deep learning for roasting coffee bean quality assessment using computer
vision in mobile environment. 2020 International Conference on Advanced Computer Science and Informa-
tion Systems (ICACSIS). IEEE, 2020, pp. 363–370. https://doi.org/10.1109/ICACSIS51025.2020.9263224.
Preprints.org (www.preprints.org) | NOT PEER-REVIEWED | Posted: 21 June 2024 doi:10.20944/preprints202406.1462.v1

31 of 34

48. Okamura, M.; Soga, M.; Yamada, Y.; Kobata, K.; Kaneda, D. Development and evaluation of roasting degree
prediction model of coffee beans by machine learning. Procedia Computer Science 2021, 192, 4602–4608.
https://doi.org/10.1016/j.procs.2021.09.238.
49. Ratanasanya, S.; Chindapan, N.; Polvichai, J.; Sirinaovakul, B.; Devahastin, S. Model-based optimization
of coffee roasting process: Model development, prediction, optimization and application to upgrading of
Robusta coffee beans. Journal of food engineering 2022, 318, 110888. https://doi.org/10.1016/j.jfoodeng.2021
.110888.
50. J, B.N.B.; M, A.N.K.; S, S.A.; Mohethe G, L.R.; Raghavendra, V. Coffee Bean Grading Based on Weight
Estimation Using Densenet121 Model. 2023 7th International Conference On Computing, Communication,
Control And Automation (ICCUBEA). IEEE, 2023, pp. 1–6. https://doi.org/10.1109/ICCUBEA58933.2023.
10392243.
51. Vilcamiza, G.; Trelles, N.; Vinces, L.; Oliden, J. A coffee bean classifier system by roast quality using
convolutional neural networks and computer vision implemented in an NVIDIA Jetson Nano. 2022
Congreso Internacional de Innovación y Tendencias en Ingeniería (CONIITI). IEEE, 2022, pp. 1–6. https:
//doi.org/10.1109/CONIITI57704.2022.9953636.
52. Naik, N.K.; Sethy, P.K. Roasted Coffee beans Classification based on Convolutional Neural Network. 2022
International Conference on Futuristic Technologies (INCOFT), 2022, pp. 1–3. https://doi.org/10.1109/
INCOFT55651.2022.10094378.
53. Caya, M.V.C.; Maramba, R.G.; Mendoza, J.S.D.; Suman, P.S. Characterization and Classification of Coffee
Bean Types using Support Vector Machine. 2020 IEEE 12th International Conference on Humanoid,
Nanotechnology, Information Technology, Communication and Control, Environment, and Management
(HNICEM). IEEE, 2020, pp. 1–6. https://doi.org/10.1109/HNICEM51456.2020.9400144.
54. Harsono, W.; Sarno, R.; Sabilla, S.I. Recognition of original arabica civet coffee based on odor using electronic
nose and machine learning. 2020 International Seminar on Application for Technology of Information and
Communication (iSemantic). IEEE, 2020, pp. 333–339. https://doi.org/10.1109/iSemantic50169.2020.923423
4.
55. Gabrieli, G.; Muszynski, M.; Thomas, E.; Labbe, D.; Ruch, P.W. Accelerated estimation of coffee sensory
profiles using an AI-assisted electronic tongue. Innovative Food Science & Emerging Technologies 2022,
82, 103205. https://doi.org/10.1016/j.ifset.2022.103205.
56. Aghdamifar, E.; Sharabiani, V.R.; Taghinezhad, E.; Szymanek, M.; Dziwulska-Hunek, A. E-nose as a non-
destructive and fast method for identification and classification of coffee beans based on soft computing
models. Sensors and Actuators B: Chemical 2023, 393, 134229. https://doi.org/10.1016/j.snb.2023.134229.
57. Suarez-Peña, J.A.; Lobaton-García, H.F.; Rodríguez-Molano, J.I.; Rodriguez-Vazquez, W.C. Machine learning
for cup coffee quality prediction from green and roasted coffee beans features. Workshop on Engineering
Applications. Springer, 2020, pp. 48–59. https://doi.org/10.1007/978-3-030-61834-6_5.
58. Wu, J.C.; Chou, T.I.; Chiu, S.W.; Shihabudeen, P.; Chen, P.A.; Tang, K.T. Development of Coffee Classification
by Feature Selection and Classifier Optimization Based on An Electronic Nose. 2023 IEEE Conference on
AgriFood Electronics (CAFE). IEEE, 2023, pp. 104–107. https://doi.org/10.1109/CAFE58535.2023.10291414.
59. Rajbharath, R.; Vijayamalaiya, S.; Aabid, M.; Salilan, A. Cofee Quality Prediction Using Machine Learning.
2023 International Conference on System, Computation, Automation and Networking (ICSCAN). IEEE,
2023, pp. 1–6. https://doi.org/10.1109/ICSCAN58655.2023.10395728.
60. Tamayo-Monsalve, M.A.; Mercado-Ruiz, E.; Villa-Pulgarin, J.P.; Bravo-Ortíz, M.A.; Arteaga-Arteaga, H.B.;
Mora-Rubio, A.; Alzate-Grisales, J.A.; Arias-Garzon, D.; Romero-Cano, V.; Orozco-Arias, S.; others. Coffee
maturity classification using convolutional neural networks and transfer learning. IEEE Access 2022,
10, 42971–42982. https://doi.org/10.1109/ACCESS.2022.3166515.
61. Anita, S.; others. Classification Cherry’s Coffee using k-Nearest Neighbor (KNN) and Artificial Neural
Network (ANN). 2020 International Conference on Information Technology Systems and Innovation (ICITSI).
IEEE, 2020, pp. 117–122. https://doi.org/10.1109/ICITSI50517.2020.9264927.
62. Raveena, S.; Surendran, R. ResNet50-based Classification of Coffee Cherry Maturity using Deep-CNN.
2023 5th International Conference on Smart Systems and Inventive Technology (ICSSIT). IEEE, 2023, pp.
1275–1281. https://doi.org/10.1109/ICSSIT55814.2023.10061006.
Preprints.org (www.preprints.org) | NOT PEER-REVIEWED | Posted: 21 June 2024 doi:10.20944/preprints202406.1462.v1

32 of 34

63. Martins, R.N.; de Carvalho Pinto, F.d.A.; de Queiroz, D.M.; Valente, D.S.M.; Rosas, J.T.F.; Portes, M.F.;
Cerqueira, E.S.A. Digital mapping of coffee ripeness using UAV-based multispectral imagery. Computers and
Electronics in Agriculture 2023, 204, 107499. https://doi.org/10.1016/j.compag.2022.107499.
64. Pineda, M.F.; Tinoco, H.A.; Lopez-Guzman, J.; Perdomo-Hurtado, L.; Cardona, C.I.; Rincon-Jimenez, A.;
Betancur-Herrera, N. Ripening stage classification of Coffea arabica L. var. Castillo using a machine
learning approach with the electromechanical impedance measurements of a contact device. Materials Today:
Proceedings 2022, 62, 6671–6678. https://doi.org/10.1016/j.matpr.2022.04.669.
65. Ngocho, B.M.; Mwangi, E.; Kamucha, G.; Jeon, G. An Image-Set of Coffee Berries for CNN Classification.
2023 IEEE AFRICON. IEEE, 2023, pp. 1–6. https://doi.org/10.1109/AFRICON55910.2023.10293226.
66. Okada, T.; Huang, Y.; Hao, G.; Iizuka, S.; Fukui, K. Low-Level Feature Aggregation Networks for Dis-
ease Severity Estimation of Coffee Leaves. 2023 18th International Conference on Machine Vision and
Applications (MVA). IEEE, 2023, pp. 1–5. https://doi.org/10.23919/MVA57639.2023.10215626.
67. Prabhu, A.; Isiri, K. A Deep Learning Approach to Identify Defects in Coffee Leaves Using Convoluional
Neural Network. 2022 International Conference on Smart Generation Computing, Communication and
Networking (SMART GENCON). IEEE, 2022, pp. 1–8. https://doi.org/10.1109/SMARTGENCON56628.202
2.10084091.
68. Montalbo, F.J.P.; Hernandez, A.A. An Optimized Classification Model for Coffea Liberica Disease using
Deep Convolutional Neural Networks. 2020 16th IEEE International Colloquium on Signal Processing & Its
Applications (CSPA). IEEE, 2020, pp. 213–218. https://doi.org/10.1109/CSPA48992.2020.9068683.
69. Paulos, E.B.; Woldeyohannis, M.M. Detection and Classification of Coffee Leaf Disease using Deep Learning.
2022 International Conference on Information and Communication Technology for Development for Africa
(ICT4DA). IEEE, 2022, pp. 1–6. https://doi.org/10.1109/ICT4DA56482.2022.9971300.
70. Raveena, S.; Surendran, R. Clustering-based Hemileia Vastatrix Disease Prediction in Coffee Leaf using Deep
Belief Network. 2023 8th International Conference on Communication and Electronics Systems (ICCES).
IEEE, 2023, pp. 1094–1100. https://doi.org/10.1109/ICCES57224.2023.10192835.
71. Lyimo, D.A.; Narasimhan, V.L.; Mbero, Z.A. Sensitivity Analysis of Coffee Leaf Rust Disease using Three
Deep Learning Algorithms. 2021 IEEE AFRICON. IEEE, 2021, pp. 1–6. https://doi.org/10.1109/AFRICON5
1333.2021.9571007.
72. Madhukar, R.K.; Chaurasiya, A.; Chaturvedi, P. A Systematized Chronicity based Disease Classification
in Coffee Leaves using Deep Learning. 2022 3rd International Conference on Smart Electronics and
Communication (ICOSEC). IEEE, 2022, pp. 1336–1342. https://doi.org/10.1109/ICOSEC54921.2022.9951915.
73. Marcos, A.P.; Rodovalho, N.L.S.; Backes, A.R. Coffee leaf rust detection using convolutional neural network.
2019 XV Workshop de Visão Computacional (WVC). IEEE, 2019, pp. 38–42. https://doi.org/10.1109/WVC.
2019.8876931.
74. Javierto, D.P.P.; Martin, J.D.Z.; Villaverde, J.F. Robusta Coffee Leaf Detection based on YOLOv3-MobileNetv2
model. 2021 IEEE 13th International Conference on Humanoid, Nanotechnology, Information Technology,
Communication and Control, Environment, and Management (HNICEM). IEEE, 2021, pp. 1–6. https:
//doi.org/10.1109/HNICEM54116.2021.9731899.
75. Geddam, L.S.; Mungara, A.; Kapavari, K.; Jayarama, K.; Tripathi, S. Detection of White Stem Borer Disease
in Coffee Plantation using Autonomous Multi Terrain Robot. 2023 19th IEEE International Colloquium on
Signal Processing & Its Applications (CSPA). IEEE, 2023, pp. 230–235. https://doi.org/10.1109/CSPA57446
.2023.10087558.
76. Lelis, A.K.; Ferriols, E.G.I.; Vallesteros, K.M.A.; Delmo, J.A.B. A Comparative Analysis of Convolutional
Neural Network Architectures for Coffee Leaf Rust Detection. 2023 IEEE International Conference on
Automatic Control and Intelligent Systems (I2CACIS). IEEE, 2023, pp. 213–218. https://doi.org/10.1109/I2
CACIS57635.2023.10193074.
77. Faisal, M.; Leu, J.S.; Darmawan, J.T. Model Selection of Hybrid Feature Fusion for Coffee Leaf Disease
Classification. IEEE Access 2023. https://doi.org/10.1109/ACCESS.2023.3286935.
78. Grimaldo, G.; Rodriguez, H.; Cabrera, V.L. Convolutional Neural Network Model for the Detection of
Diseases and Pests in Coffee Crops. 2022 8th International Engineering, Sciences and Technology Conference
(IESTEC). IEEE, 2022, pp. 684–690. https://doi.org/10.1109/IESTEC54539.2022.00113.
79. Yamashita, J.V.Y.B.; Leite, J.P.R. Coffee disease classification at the edge using deep learning. Smart
Agricultural Technology 2023, 4, 100183. https://doi.org/10.1016/j.atech.2023.100183.
Preprints.org (www.preprints.org) | NOT PEER-REVIEWED | Posted: 21 June 2024 doi:10.20944/preprints202406.1462.v1

33 of 34

80. Tassis, L.M.; Krohling, R.A. Few-shot learning for biotic stress classification of coffee leaves. Artificial
Intelligence in Agriculture 2022, 6, 55–67. https://doi.org/10.1016/j.aiia.2022.04.001.
81. Milke, E.B.; Gebiremariam, M.T.; Salau, A.O. Development of a coffee wilt disease identification model using
deep learning. Informatics in Medicine Unlocked 2023, 42, 101344. https://doi.org/10.1016/j.imu.2023.101344.
82. Tuesta-Monteza, V.A.; Mejia-Cabrera, H.I.; Arcila-Diaz, J. CoLeaf-DB: Peruvian coffee leaf images dataset
for coffee leaf nutritional deficiencies detection and classification. Data in Brief 2023, 48, 109226. https:
//doi.org/10.1016/j.dib.2023.109226.
83. Abuhayi, B.M.; Mossa, A.A. Coffee disease classification using Convolutional Neural Network based on
feature concatenation. Informatics in Medicine Unlocked 2023, 39, 101245. https://doi.org/10.1016/j.imu.2023
.101245.
84. Esgario, J.G.; de Castro, P.B.; Tassis, L.M.; Krohling, R.A. An app to assist farmers in the identification of
diseases and pests of coffee leaves using deep learning. Information Processing in Agriculture 2022, 9, 38–47.
https://doi.org/10.1016/j.inpa.2021.01.004.
85. Jepkoech, J.; Mugo, D.M.; Kenduiywo, B.K.; Too, E.C. Arabica coffee leaf images dataset for coffee leaf
disease detection and classification. Data in brief 2021, 36, 107142. https://doi.org/10.1016/j.dib.2021.107142.
86. Sorte, L.X.B.; Ferraz, C.T.; Fambrini, F.; dos Reis Goulart, R.; Saito, J.H. Coffee leaf disease recognition
based on deep learning and texture attributes. Procedia Computer Science 2019, 159, 135–144. https:
//doi.org/10.1016/j.procs.2019.09.168.
87. Tassis, L.M.; de Souza, J.E.T.; Krohling, R.A. A deep learning approach combining instance and semantic
segmentation to identify diseases and pests of coffee leaves from in-field images. Computers and Electronics
in Agriculture 2021, 186, 106191. https://doi.org/10.1016/j.compag.2021.106191.
88. Ventura, J.; Esgario, J.; Krohling, R. Deep learning for classification and severity estimation of coffee leaf biotic
stress. Computers and Electronics in Agriculture 2020, 169. https://doi.org/10.1016/j.compag.2019.105162.
89. de Oliveira Aparecido, L.E.; Lorençone, P.A.; Lorençone, J.A.; Torsoni, G.B.; de Lima, R.F.; Padilha, F.;
de Souza, P.S.; de Souza Rolim, G. Addressing coffee crop diseases: forecasting Phoma leaf spot with machine
learning. Theoretical and Applied Climatology 2023, pp. 1–22. https://doi.org/10.1007/s00704-023-04739-z.
90. de Oliveira Aparecido, L.E.; de Souza Rolim, G.; da Silva Cabral De Moraes, J.R.; Costa, C.T.S.; de Souza, P.S.
Machine learning algorithms for forecasting the incidence of Coffea arabica pests and diseases. International
Journal of Biometeorology 2020, 64, 671–688. https://doi.org/10.1007/s00484-019-01856-1.
91. Selvanarayanan, R.; Rajendran, S. Roaming the Coffee Plantations Using Grey Wolves Optimisation and
the Restricted Boltzmann Machine to Predict Coffee Berry Disease. 2023 International Conference on Self
Sustainable Artificial Intelligence Systems (ICSSAS). IEEE, 2023, pp. 681–689. https://doi.org/10.1109/
ICSSAS57918.2023.10331629.
92. Caballero, E.M.T.; Duke, A.M.R. Implementation of artificial neural networks using nvidia digits and opencv
for coffee rust detection. 2020 5th International Conference on Control and Robotics Engineering (ICCRE).
IEEE, 2020, pp. 246–251. https://doi.org/10.1109/ICCRE49379.2020.9096435.
93. Latif, M.A.; Afshan, N.; Mushtaq, Z.; Khan, N.A.; Irfan, M.; Nowakowski, G.; Alqhtani, S.M.; Mursal, S.;
Telenyk, S. Enhanced classification of coffee leaf biotic stress by synergizing feature concatenation and
dimensionality reduction. IEEE Access 2023. https://doi.org/10.1109/ACCESS.2023.3314590.
94. Parraga-Alava, J.; Cusme, K.; Loor, A.; Santander, E. RoCoLe: A robusta coffee leaf images dataset for
evaluation of machine learning based methods in plant diseases recognition. Data in brief 2019, 25, 104414.
https://doi.org/10.1016/j.dib.2019.104414.
95. Jindal, V.; Kukreja, V.; Bhattacherjee, A.; Rana, S.; Mehta, S. Agricultural Innovation: Unleashing Federated
Learning CNNs on Coffee Leaf Disease Severity Analysis. Communication, and Intelligent Systems (ICCCIS)
2023, pp. 782–787. https://doi.org/10.1109/ICCCIS60361.2023.10425426.
96. Marin, D.B.; Santana, L.S.; Barbosa, B.D.S.; Barata, R.A.P.; Osco, L.P.; Ramos, A.P.M.; Guimarães, P.H.S.;
others. Detecting coffee leaf rust with UAV-based vegetation indices and decision tree machine learning
models. Computers and Electronics in Agriculture 2021, 190, 106476. https://doi.org/10.1016/j.compag.2021.1
06476.
97. Ruttanadech, N.; Phetpan, K.; Srisang, N.; Srisang, S.; Chungcharoen, T.; Limmun, W.; Youryon, P.; Kong-
tragoul, P. Rapid and accurate classification of Aspergillus ochraceous contamination in Robusta green
coffee bean through near-infrared spectral analysis using machine learning. Food Control 2023, 145, 109446.
https://doi.org/10.1016/j.foodcont.2022.109446.
Preprints.org (www.preprints.org) | NOT PEER-REVIEWED | Posted: 21 June 2024 doi:10.20944/preprints202406.1462.v1

34 of 34

98. Kulkarni, S.; N C, K.; C K, S.; Pal, S.; Dash, S.; Shenoy, P.D.; K R, V. Coffee Plant Disease Identification
using Enhanced Short Learning EfficientNetV2. 2023 IEEE 20th India Council International Conference
(INDICON), 2023. https://doi.org/10.1109/INDICON59947.2023.10440883.
99. Kulkarni, S.; H N, S.; V, V.M.; Shenoy, P.D.; R, V.K. Detection of Coffee Leaf Diseases using DenseNet-264 and
SLIC Segmentation. 2023 10th IEEE Uttar Pradesh Section International Conference on Electrical, Electronics
and Computer Engineering (UPCON), 2023, Vol. 10, pp. 769–774. https://doi.org/10.1109/UPCON59197.2
023.10434875.
100. Sosa, J.; Ramírez, J.; Vives, L.; Kemper, G. An Algorithm For Detection of Nutritional Deficiencies from Digital
Images of Coffee Leaves Based on Descriptors and Neural Networks. 2019 XXII Symposium on Image, Signal
Processing and Artificial Vision (STSIVA), 2019, pp. 1–5. https://doi.org/10.1109/STSIVA.2019.8730286.
101. Rajus, S.; Bhagavan, S.G.; Kharva, H.; Rao, S.; Olsson, S.B. Behavioral Ecology of the Coffee White Stem Borer:
Toward Ecology-Based Pest Management of India’s Coffee Plantations. Frontiers in ecology and evolution 2021,
9, 607555. https://doi.org/10.3389/fevo.2021.607555.

Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those
of the individual author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s)
disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or
products referred to in the content.