Special Issue - 2022 International Journal of Engineering Research & Technology (IJERT)

ISSN: 2278-0181
ETEDM – 2022 Conference Proceedings

Plant Leaf Disease Detection using Deep Learning

Mr. Thangavel. M -AP/ECE , Gayathri P K , Sabari K R, Prathiksha V
Knowledge Institute of Technology,
Salem

Abstract:- The latest improvements in computer vision Deep learning is the advanced methods of machine
formulated through deep learning have paved the method for learning that uses neural networks that works like the
how to detect and diagnose diseases in plants by using a human brain Traditional methods involve the use of
camera to capture images as basis for recognizing several semantic features as theclassification method.
types of plant diseases. This study provides an efficient
A convolutional neural network (CNN) is a deep
solution for detecting multiple diseases in several plant
varieties. The system was designed to detect and recognize learning model that is widely used in image processing.
several plant varieties specifically apple, corn, grapes, potato, The work of Lee et al. presents a hybrid model to
sugarcane, and tomato. The system can also detect several obtain characteristicsof leaves using CNN and classify the
diseases of plants. extracted features of leaves. The methodology in the
Comprised of 35,000 images of healthy plant leaves and study involves three key stages: acquisition of data, pre-
infected with the diseases, the researchers were able to train processing of data and image classification. The study
deep learning models to detect and recognize plant diseases utilized dataset from Plant village dataset that contains
and the absence these of diseases. The trained model plant varieties of apple, corn, grapes, potato,
hasachieved an accuracy rate of 96.5% and the system was
sugarcane, and tomato. There are 11 types of plant
able toregister up to 100% accuracy in detecting and
recognizing theplant variety and the type of diseases the plant diseases identified in the study including healthy
was infected. images of identified plants. Image pre-processing
involves re-sized images and enhancement before
Keywords: Plant disease recognition, deep learning, computer supplying it for the
vision, convolutional neural network classification model.

INTRODUCTION CONVULUTIONAL NEURAL NETWORK

Deep learning is a subsection of Artificial Intelligence
Early plant disease detection plays a significant role in and machine learning that uses artificial neural networks
efficient crop yield. Plant diseases like black measles, black (ANN). Training the deep learning models divides the
rot, bacterial spot, etc. affect the growth, crop quality of feature extraction and extracts its features for
plants and economic impacts in the agriculture industry. To classification. There are several applications of deep
avoid the impact of these diseases, expensive approaches learning which include computer vision, image
and the use of pesticides are some solutions the farmers classification, restoration, speech, video analysis,etc.
usually implement.
A convolutional neural network with nominal process
The use of chemical means damages the plant and the can simply detect and categorize. It is efficient in
surrounding environment. In addition, this kind of evaluating graphical images and extracts the essential
approach intensifies the cost of production and major features through its multi-layered structure. As shown in
monetary loss to farmers. Early discovery of diseases as Fig. 1, the CNN involves four layers, that is: input image,
they occur is the most important period for efficient convolutional layer and pooling layer, fully connected
disease management. Manual disease detection through layers, and output.
human experts to identify and recognize plant diseases is a
usual practice in agriculture . With the improvements in
technology, automatic detection of plant diseases from raw
images is possible through computer vision and artificial
intelligence researches . In this study, the researchers were
able to investigate plant diseases and pest’s infestation that
affects the leaves of the plants.

Image processing techniques are now commonly

employed in agriculture and it is applied for the detection
and recognition of weeds, fruit-grading, identifying and
calculating disease infestations of plants ,and plant
genomics. Currently, the introduction of deep learning
methods turns out to be popular

Volume 10, Issue 08 Published by, www.ijert.org 34

Special Issue - 2022 International Journal of Engineering Research & Technology (IJERT)
ISSN: 2278-0181
ETEDM – 2022 Conference Proceedings

Fig. 3. Pooling operation

C. Activation Layer
Utilizes a non-linear ReLU (Rectified Linear Unit)
Fig 1. Illustration of Convolutional Neural Network Architecture activation layer in every convolution layer. The application of
dropout layers to prevent overfitting is also applied in this
A. Convolutional Layer layer.
Convolutional layers store the output of the kernels from the
previous layer which consists of weights and biases to be D. Fully Connected Layer
learned. The generated kernels that represent the data without This layer is used to analyze the class probabilities and the
an error is the point of the optimization function. In this layer, a output is the input of the classifier. Softmax classifier is the
sequence of mathematical processes is done to extract the well-known input classifier and recognition and classification
feature map of the input image .Fig. 2 exhibits the operation of of sugarcane diseases are applied in this layer.
the convolution layer for a 5x5 image input and a result is a 3x3
filter that reduced to a smaller size . Also, the figure shows the Methodology
shifting of filter starting from the upper left corner of the input
image. The values for each step are thenmultiplied by the values A block diagram presented in Fig. 4 shows the Input Dataset,
of the filter and the added values are the result. A new matrix Image Acquisition, Image pre-processing and Classification.
with the reduced size is formed from the input image.

Dataset

Image Acquisition

Image Pre-processing

Classification

Fig. 2 5x5 input and 3x3 filter operation of convolution layer. Fig. 4 Plant leaf detection and disease recognition methodology

B. Pooling Layer A. Image Acquisition

This layer reduces overfitting and lowers the neuron size for Image dataset used for training the model was acquired in
the downsampling layer. Fig. 3 illustrates an example of the the Plant Village repository [15]. A python script was used to
pooling operation. This layer reduces the feature map size, download images of the plant diseases from the repository. The
reduce parameter numbers, training-time, computation rate and acquired dataset consists of approximately 35,000 images with
controls overfitting [20]. Overfitting is defined by a modelby 32 different classes plant varieties and diseases.
achieving 100% on the training dataset and 50% on test data.
ReLU and max pooling were utilized to lower feature map B. Image Pre-processing
dimensions [21]. Pre-processed images are reduced image size and image crop
to a given input. It processes and enhances the image to its
needed color scale. The study uses colored and resized images
to 96x96 resolution for processing.

C. Classification
Classification uses a fully connected layers and for feature
extraction it uses convolutional and pooling layers. The
classification process classifies the plant leaf if it is infected

Volume 10, Issue 08 Published by, www.ijert.org 35

 Special Issue - 2022 International Journal of Engineering Research & Technology (IJERT)
ISSN: 2278-0181
ETEDM – 2022 Conference Proceedings

with the disease or not, identifies the type of plant disease and
recognize the plant variety.

Experimental Settings

The dataset consists of approximately 35,000 images

containing 9 different types of tomato leaf diseases, 4 different
types of grape leaf diseases, 4 different types of corn leaf
diseases, 4 different types of apple leaf diseases, and 6 different
types of sugarcane diseases. A neural network application
program interface (API) written in Python was applied for the
CNN model application. All the image dataset was used for
training and testing uses 1,000 images that was taken from the
field. Data augmentation techniques were integrated into the
application to enhance the image dataset byrotating the images
to 25 degrees, flipping and shifting of images horizontally and
vertically. Adam optimizer is incorporated using a categorical
cross-entropy. The modeltrained 75 epochs using a batch size Fig. 5 Accuracy and loss against epochs
of 32. All the experimentations were performed on Dell
Inspiron 14-3476 i5processor and memory size of 16GB.

Results and Analysis

A 96.5% accuracy rate was achieved using 75 epochs during

the training of the model. The model also achieved a maximum
accuracy rate of 100% when testing random images of plant
varieties and diseases. The visualization of plots of train and
test accuracy is described in fig 5. shows the model is effective
in detecting and recognizing plant diseases.
Fig. 6 shows of detection and recognition of a corn plant with
100% accuracy and it shows an accuracy rate of 100%
recognition of healthy plant leaf on the left image and 99.56% Fig. 6 Result of detection and recognition of a corn plant with 100%
affected with gray leaf spot disease on the right image. Fig. 7 accuracy and shows a healthy plant leaf on the left image and diseased
shows the result of 99.77% and 99.58% accuracy of detecting infected plant on the right image.
and recognizing a tomato plant and it shows a 99.62% accuracy
rate that it is infected with a late blight disease on theleft image
and 75.36% infected of early blight disease on the right image.
Fig. 8 shows a 100% result of detection and recognition of a
grape plant and shows a 100% rate that the leafis infected with
a late blight disease on the left image and 95.09% infected with
a black rot disease on the right image. Fig. 9 shows the result
of the detection and recognition of an apple plant with 100%
accuracy and shows a 100% result that the leaf is infected with
a black rot disease on the left image and a 99.99% that it is a
healthy leaf on the right image.

Fig. 7 Result of detection and recognition of a tomato plant with 99%

accuracy and shows a leaf infected with a late blight disease on the left
image and early blight disease on the right image.

Volume 10, Issue 08 Published by, www.ijert.org 36

 Special Issue - 2022 International Journal of Engineering Research & Technology (IJERT)
ISSN: 2278-0181
ETEDM – 2022 Conference Proceedings
Journal of Engineering Research in Africa, 24, pp 124-136, 2016,
Fig. 8 Result of detection and recognition of a grape plant with 100% 10.4028/www.scientific.net/JERA.24.124.
accuracy and shows a leaf infected with a late blight disease on the left [9] Y. Su, F. Jurie. Improving Image Classification Using Semantic
image and black rot disease on the right image. Attributes, International Journal of Computer Vision, Springer
Verlag, 2012, 100 (1), pp.59-77. 10.1007/s11263-012-0529-4.
[10] Y. LeChun, Y. Bengio and G. Hinton, Deep Learning, Nature,
vol. 521, pp. 436-444, 2015. eprint
https://doi.org/10.1038/nature14539
[11] S. H. Lee, C. S. Chan, S. J. Mayo and P. Remagnino, How deep
learning extracts and learns leaf features for the plant
classification, Pattern Recognition, vol. 71, pp. 1-13, 2017.
[12] K.P. Ferentinos, Deep learning models for plant disease
detection and diagnosis, Computers and Electronics in
Agriculture, vol. 145, pp. 311-318, 2018
[13] H. Durmus, E. O. Gunes¸ and M. Kirci, Disease detection on the
leaves of the tomato plants by using deep learning, In Agro-
Geoinformatics, IEEE 6th International Conference on, pp. 1-5,
Fig. 9 Result of detection and recognition of an apple plant with 100% 2017.
accuracy and shows a leaf infected with a black rot disease on the left [14] H. A. Atabay, Deep residual learning for tomato plant leaf
image and a healthy leaf on the right image. disease identification, Journal of Theoretical & Applied
Information Technology, vol. 95 no. 24 pp. 6800-6808, 2017.
Conclusion [15] D.P. Hughes, and M. Salathé, An open access repository of
images on plant health to enable the development of mobile
The people around the world rely on the agricultural sector disease diagnostics, arXiv:1511.08060, 2015
as one of the most important sectors where crops are the basic [16] V. Tumen, O. F. Soylemez and B. Ergen, Facial emotion
need for food. Early recognition and detection of these diseases recognition on a dataset using convolutional neural network,
2017 International Artificial Intelligence and Data Processing
are crucial to the agricultural industry. This paper has achieved
Symposium (IDAP), 2017.
its goal to detect and recognize 32 different plant varieties and [17] A. Krizhevsky, I. Sutskever, and G. H. E. Hinton, ImageNet
plant diseases using convolutional neural network. The trained Classification with Deep Convolutional Neural Networks, in
model can be used to test real-time images to detect and advances in Neural Information Processing Systems, 2012.
recognize plant diseases. For the future work, additional plant [18] F. N. Iandola, S. Han, M. W. Moskewicz, K. Ashraf, W. J. Dally,
varieties and different types of plant diseases may be included and K. Keutzer, Squeezenet: AlexNet-Level Accuracy with 50x
in the existing dataset to increase the trained models. Other Fewer Parameters and <0.5MB Model Size, eprint
CNN architectures may also use different learning rates and arXiv:1602.07360v4, pp. 1-13, 2016
optimizers for experimenting the performance and accuracy of
the model. With the achieved accuracy of 96.5%, the proposed
model can assist farmers to detect and recognize plant diseases.

References

[1] H. Park, J. S. Eun and S. H. Kim, Image-based disease diagnosing

and predicting of the crops through the deep learning mechanism,
In Information and Communication Technology Convergence
(ICTC), IEEE 2017 International Conference on, pp. 129-131,
2017.
[2] K. Elangovan and S. Nalini, Plant disease classification using
image segmentation and SVM techniques, International Journal of
Computational Intelligence Research, vol. 13(7), pp. 1821-1828,
2017.
[3] A. Vibhute and S. K. Bodhe, Applications of Image Processing in
Agriculture: A Survey, International Journal of Computer
Applications, vol. 52, no. 2, pp. 34-40, 2012.
[4] S. Militante, Fruit Grading of Garcinia Binucao (Batuan) using
Image Processing, International Journal of Recent Technology
and Engineering (IJRTE), vol. 8 issue 2, pp. 1829- 1832, 2019
[5] J. G. B. Garcia, Digital Image Processing Techniques for
Detecting, Quantifying and Classifying Plant Diseases, Springer
Plus, 2013.
[6] A. M. Mutka and R. S. Bart, Image-Based Phenotyping of Plant
Disease Symptoms, Frontiers in Plant Science, vol. 5, pp. 1-8,
2015.
[7] S.P. Mohanty, D.P. Hughes, and M. Salathé Using deep learning
for image-based plant disease detection, in Frontiers in plant
science 7, p. 1419, 2016.
[8] B. Benuwa, Y. Zhao Zhan, B. Ghansah, D. Wornyo, & F.
Banaseka, A Review of Deep Machine Learning, International

Volume 10, Issue 08 Published by, www.ijert.org 37