Emergence of Digital Image

Processing in Agriculture Sector

Submitted by:
Kratika Bhargava

Uttam Institute of Management

Studies, Agra
 Project Report

Submitted by:
Kratika Bhargava
Register No.- PREERN220018693

Under the guidance of

Mr. Ashish Raitani

In partial fulfilment of the requirements

For the award of the Degree of
Master of Business Administration

Dr. APJ Abdul Kalam Technical

University, Lucknow
 DECLARATION

I undersigned, hereby declare that the project title Emergence of Digital Image

Processing in Agriculture Sector, Submitted in partial fulfilment for the award of

Degree of Master of Business Administration of Dr. APJ Abdul Kalam Technical

University is a bonafide record of work done by me under the guidance of Mr.

Ashish Raitani, Uttam Institute of Management Studies. This report has not been

previously formed on the basis for the award of any degree, diploma, or similar

title of any University.

Date: Kratika Bhargava

 CERTIFICATE

This is to certify that the report titled Emergence of Digital Image Processing in

Agriculture Sector, being submitted by Kratika Bhargava. Register No.-

PREERN220018693, in partial fulfilment of the requirements for the award of the

Degree of Master of Business Administration, is a bonafide record of the project

work done by Kratika Bhargava of Uttam Institute of Management Studies, Agra.

Mr. Ashish Raitani Dr. Vikrant Shastri

Asst. professor Director

 ACKNOWLEDGEMENT

Through this acknowledgement I express my sincere gratitude towards all those

people who helped me in this project, which has been a learning experience.

This space wouldn’t be enough to extend my warm gratitude towards my project

guide Mr. Ashish Raitani for his efforts in coordinating with my work and guiding
me in the right direction.

I escalate a heartfelt regard to our Institution Director, Dr. Vikrant Shastri for
giving me the essential hand in concluding this work.

It would be injustice to proceed without acknowledging those vital supports I

received from my beloved classmates and friends, without whom I would have
been half done. I also use this space to offer my sincere love to my family and all
others who had been there, helping me walk through this work.

Kratika Bhargava
 Table Of Content

Serial Topics Page

No. No.
1. Chapter 1: Introduction
1.1 What is Digital Image Processing?
1.2 Image Sensor
1.3 Image Compression
1.4 Digital Signal Processor (DSP)
1.5 Medical Imaging

2. Chapter 2: Tools of Digital Image

Processing and Implementation
2.1 Introduction
2.2 A brief literature on ML & AI
2.3 Best AI Tools for Image Processing
2.3.1 TensorFlow
2.3.2 PyTorch
2.3.3 OpeCV
2.3.4 Caffee
2.3.5 MATLAB Image Processing Toolbox
2.3.6 Microsoft Computer Vision
2.3.7 Google Colaboratory (Colab)
2.4 Implementation
2.4.1 In Production Automation
2.4.2 In Agricultural Landscape
2.4.3 Biomedical and Other Healthcare Applications
2.4.4 Disaster Management

3. Chapter 3: Digital Image Processing

in Agriculture
3.1 Introduction
3.2 Digital Image Processing based Applications in
Agriculture
3.3 Application areas of Digital Image processing in
agricultural field
3.3.1 Identification of Nutrient inadequacies and plant
content
3.3.2 Fruits quality grading, sorting and inspection
3.3.3 Object tracking, land and crop estimation
3.3.4 Crop Management
3.4 Applications based on Imaging Techniques
3.5 Importance of Digital Image Processing in
Agriculture
4. Conclusion
5. Bibliography
 Chapter 1: Introduction

1.1. What is Digital Image Processing?

Digital image processing is the use of a digital computer to process digital images
through an algorithm. As a subcategory or field of digital signal processing, digital
image processing has many advantages over analog image processing. It allows a
much wider range of algorithms to be applied to the input data and can avoid
problems such as the build-up of noise and distortion during processing. Since
images are defined over two dimensions (perhaps more) digital image processing
may be modelled in the form of multidimensional systems. The generation and
development of digital image processing are mainly affected by three factors: first,
the development of computers; second, the development of mathematics
(especially the creation and improvement of discrete mathematics theory); third,
the demand for a wide range of applications in environment, agriculture, military,
industry and medical science has increased.
Many of the techniques of digital image processing, or digital picture processing as
it often was called, were developed in the 1960s, at Bell Laboratories, the Jet
Propulsion Laboratory, Massachusetts Institute of Technology, University of
Maryland, and a few other research facilities, with application to satellite imagery,
wire-photo standards conversion, medical imaging, videophone, character
recognition, and photograph enhancement. The purpose of early image processing
was to improve the quality of the image. It was aimed for human beings to improve
the visual effect of people. In image processing, the input is a low-quality image,
and the output is an image with improved quality. Common image processing
includes image enhancement, restoration, encoding, and compression. The first
successful application was the American Jet Propulsion Laboratory (JPL). They
used image processing techniques such as geometric correction, gradation
transformation, noise removal, etc. on the thousands of lunar photos sent back by
the Space Detector Ranger 7 in 1964, taking into account the position of the sun
and the environment of the moon. The impact of the successful mapping of the
moon's surface map by the computer has been a huge success. Later, more complex
image processing was performed on the nearly 100,000 photos sent back by the
spacecraft, so that the topographic map, colour map and panoramic mosaic of the
moon were obtained, which achieved extraordinary results and laid a solid
foundation for human landing on the moon.

1.2. Image Sensor

The basis for modern image sensors is metal-oxide-semiconductor (MOS)

technology, which originates from the invention of the MOSFET (MOS field-
effect transistor) by Mohamed M. Atalla and Dawon Kahng at Bell Labs in 1959.
This led to the development of digital semiconductor image sensors, including the
charge-coupled device (CCD) and later the CMOS sensor. The charge-coupled
device was invented by Willard S. Boyle and George E. Smith at Bell Labs in
1969. While researching MOS technology, they realized that an electric charge was
the analogy of the magnetic bubble and that it could be stored on a tiny MOS
capacitor. As it was fairly straightforward to fabricate a series of MOS capacitors
in a row, they connected a suitable voltage to them so that the charge could be
stepped along from one to the next. The CCD is a semiconductor circuit that was
later used in the first digital video cameras for television broadcasting.

The NMOS active-pixel sensor (APS) was invented by Olympus in Japan during
the mid-1980s. This was enabled by advances in MOS semiconductor device
fabrication, with MOSFET scaling reaching smaller micron and then sub-micron
levels. The NMOS APS was fabricated by Tsutomu Nakamura's team at Olympus
in 1985. The CMOS active-pixel sensor (CMOS sensor) was later developed by
Eric Fossum's team at the NASA Jet Propulsion Laboratory in 1993. By 2007,
sales of CMOS sensors had surpassed CCD sensors.
1.3. Image Compression

An important development in digital image compression technology was the

discrete cosine transform (DCT), a lossy compression technique first proposed by
Nasir Ahmed in 1972. DCT compression became the basis for JPEG, which was
introduced by the Joint Photographic Experts Group in 1992. JPEG compresses
images down to much smaller file sizes, and has become the most widely used
image file format on the Internet. Its highly efficient DCT compression algorithm
was largely responsible for the wide proliferation of digital images and digital
photos, with several billion JPEG images produced every day as of 2015.

1.4. Digital Signal Processor (DSP)

Electronic signal processing was revolutionized by the wide adoption of MOS

technology in the 1970s. MOS integrated circuit technology was the basis for the
first single-chip microprocessors and microcontrollers in the early 1970s, and then
the first single-chip digital signal processor (DSP) chips in the late 1970s. DSP
chips have since been widely used in digital image processing.
The discrete cosine transform (DCT) image compression algorithm has been
widely implemented in DSP chips, with many companies developing DSP chips
based on DCT technology. DCTs are widely used for encoding, decoding, video
coding, audio coding, multiplexing, control signals, signalling, analog-to-digital
conversion, formatting luminance and colour differences, and colour formats such
as YUV444 and YUV411. DCTs are also used for encoding operations such as
motion estimation, motion compensation, inter-frame prediction, quantization,
perceptual weighting, entropy encoding, variable encoding, and motion vectors,
and decoding operations such as the inverse operation between different colour
formats (YIQ, YUV and RGB) for display purposes. DCTs are also commonly
used for high-definition television (HDTV) encoder/decoder chips.

1.5. Medical Imaging

In 1972, the engineer from British company EMI Housfield invented the X-ray
computed tomography device for head diagnosis, which is what is usually called
CT (computed tomography). The CT nucleus method is based on the projection of
the human head section and is processed by computer to reconstruct the cross-
sectional image, which is called image reconstruction. In 1975, EMI successfully
developed a CT device for the whole body, which obtained a clear tomographic
image of various parts of the human body. In 1979, this diagnostic technique won
the Nobel Prize. Digital image processing technology for medical applications was
inducted into the Space Foundation Space Technology Hall of Fame in 1994.
 Chapter 2: Tools of Digital Image Processing and
Implementation

2.1. Introduction

Image processing is a very useful technology and the demand from the industry
seems to be growing every year. Historically, image processing that uses machine
learning appeared in the 1960s as an attempt to simulate the human vision system
and automate the image analysis process. As the technology developed and
improved, solutions for specific tasks began to appear.

The rapid acceleration of computer vision in 2010, thanks to deep learning and the
emergence of open source projects and large image databases only increased the
need for image processing tools.

Currently, many useful libraries and projects have been created that can help you
solve image processing problems with machine learning or simply improve the
processing pipelines in the computer vision projects where you use ML.

2.2. A Brief Literature on DIP in ML & AI

Machines get introduced to analyze images the exact way human brains do and
explore those images much more positively than a human can. Therefore, image
processing with AI can power face recognition and authentication functionality.
Thus, it guarantees safety in public places catch and identify objects and designs in
images and videos.
Presently, image processing is a beneficial technology, and the demand from the
industry appears to be growing every year. Therefore, image processing that uses
ML appeared in the 1960s as a shot to mimic the human vision system and
automate the image research process. Thus, as the technology evolved and
enhanced, answers for exact tasks appeared.

Therefore, the fast acceleration of computer vision in 2010, appreciations to deep

learning, and the emergence of open-source projects and large image databases
only raised the market for image processing tools. Thus, many valuable libraries
and projects help crack image processing concerns with machine learning or
enhance the processing pipelines in computer vision projects.

2.3. Best AI tools for Image Processing

2.3.1. TensorFlow
Google‘s TensorFlow is a famous open-source framework for machine
learning and deep learning. Thus, using TensorFlow, one can build and
prepare custom deep learning models. Therefore, the framework also
contains a set of libraries, which can be used in image processing
assignments and computer concept applications.

However, it was created to unravel issues of constructing and familiarizing a

neural network to automatically discover and categorize images, comparing
the quality of human perception.
 Functionality:

 Work on numerous parallel processors

 Analysis through multidimensional data arrays – tensors
 Optimization for tensor processors
 Rapid model iteration
 Uncomplicated debugging
 Own logging system
 Interactive log visualizer

2.3.2. PyTorch

PyTorch is an open-source ML and deep learning framework formed by the

Facebook AI Research lab (FAIR). Thus, this Torch-based framework includes
Python, C++, and Java interfaces.
Also, one can use PyTorch for producing computer vision and NLP applications.
Therefore, it also speeds up the development process from research prototyping to
industrial development.

Functionality:

 Effortless transition to production

 Distributed learning and execution optimization
 A rich ecosystem of tools and libraries
 Adequate support for major cloud platforms
 Optimization and automated differentiation modules

2.3.3. OpenCV

It is an open-source library that involves machine learning and image processing

algorithms. Also, it is an open-source computer vision library. Thus, it is
developed and nicely optimized for real-time computer vision applications. Also, it
creates an open infrastructure.

Functionality:

 Fundamental data structures

 Image processing algorithms
 Primary algorithms for computer vision
 Input and output of images and videos
 Human face detection
 Search for stereo matches
 Optical flow
 Continued integration system
 CUDA-optimized architecture
 Android version
 Java API
 Built-in performance testing system
 Cross-platform

2.3.4. Caffe

A deep learning framework concentrated on cracking the image type and

segmentation concern.

Functionality:

 Analysis using blobs – multidimensional data arrays operated in parallel

computing
 Model definition and design optimization, no hard coding
 Comfortable switching between CPU and GPU
 High speed of work
2.3.5. MATLAB Image Processing Toolbox

MATLAB stands for matrix laboratory. Hence, it‘s the name of both a famous
platform for decoding scientific and mathematical situations and a programming
language. Thus, this medium delivers an Image Processing Toolbox (IPT) that
contains numerous algorithms. Hence, it also contains workflow applications for
AI-based image analysis, processing, and devising algorithms. MATLAB IPT isn‘t
an open-source platform. Hence, it has a free trial.

Functionality:
 Automates familiar image processing workflows
 Used for noise reduction, image enhancement, and image segmentation
 3D images processing
 IPT functions support C/C++ code generation and are for deploying embedded
vision systems and desktop prototyping.

2.3.6. Microsoft Computer Vision

Computer Vision is a cloud-based service delivered by Microsoft. Therefore, it

gives access to evolved algorithms for image processing and information
extraction.

Functionality:
 Analyses visual features and characteristics of an image
 Allows to moderate image content
 Extract text from images.

2.3.7. Google Colaboratory (Colab)

Google Colaboratory (Colab) is a free cloud service. Therefore, it improves coding

skills and develops deep learning applications from scratch.

Accordingly, it also uses popular libraries such as Keras and TensorFlow while
designing an AI-based application. Thus, this service is based on Jupyter
Notebooks, letting AI developers share their wisdom and expertise.

Functionality:

 Colab delivers free GPU resources

 Allows to transfer, comment, and collaborate on the same document with
multiple people.

2.4. Implementation
Image processing technology extracts information from images and integrates it
for a wide range of applications. Here, we‘ve outlined the most prominent fields
where image processing could bring significant benefits.

2.4.1. In Production Automation

Image processing applications can make it possible for machines to act as more
self-sufficient and ensure the quality of products. Assuming processing systems
work faster than humans, inline quality controls like 100% controls can be very
quickly implemented. Damaged parts can be replaced or corrected, which would
lead to more efficacies of production facilities. With the help of advanced image
processing technologies, even an entire production facility can be managed.

2.4.2. In Agricultural Landscape

Key concerns in agriculture include quality of yield and water stress. Irrigation
monitoring and providing information can be made possible by tracking satellite
imaging of the fields. Processing of infrared images can act as an additional means
to monitor and analyze irrigation. This analysis can then be utilized in pre-
harvesting operations for deciding whether to harvest or not. Growth of weeds can
also be detected by using a combination of machine learning and image processing
algorithms and techniques. Quality of yields can be ensured by the reliable and
accurate method of image processing through sorting and grading of fresh
products.

2.4.3. Biomedical and Other Healthcare Applications

3D imaging is a process where a 2D image is converted into a 3D image by

creating the optical illusion of depth. The next step is rendering where colours and
textures are included in the 3D model to make it look realistic. With such 3D
imaging and rendering, doctors can see extremely high quality 3D images of
organs that they couldn‘t have seen otherwise. This, in turn, can help them carry
out delicate surgeries and make accurate diagnoses.

2.4.4. Disaster management

Drone aircrafts monitoring environmental and traffic conditions can use image
processing to capture high resolution real-time videos and photographs. In case of
natural or other disasters like flood, earthquake, fire etc., knowing which disaster-
struck areas the authorities need to focus upon can help save lives by reaching
quickly to those trapped and bring them out safely. Even monitoring the progress
and ensuring co-ordination during such rescue operations can be made easier with
real-time image processing techniques.
 Chapter 3: Digital Image Processing in Agriculture

3.1. Introduction

Agriculture is a significant part of an economy that gives essential needs and

nourishment for people. Advances in the area of innovation and science made
another revolution in the agricultural segment. The job of information technology
has expanded the potential of the agricultural segment by utilizing the automated
system in different exercises. New advancements like precision agriculture, GPS,
sensor systems, robotics have risen with ongoing developments and advancements
in the agriculture segment. Digital Image Processing, Machine Vision and
Computer Vision are different procedures utilized in the advancement of an
automated system to serve their different purposes. In the application of agriculture
science, for example, digital image processing, distributed and parallel computing
decreases the computational time and thus, plant acknowledgement can be made a
lot quicker.
India is a cultivating country; wherein about 70 per cent of the populace depends
upon farming. For high yield and quality, farmers choose suitable fruits and
vegetable crops from a wide range of crops. The cultivation of these crops requires
highly sophisticated techniques for specialization. Computer use among
agriculturists and other farming experts has risen quickly previously and future
ramification for agricultural software decade. Image analysis is a powerful tool for
the non-destructive investigation of agricultural items, which is generally utilized
in agribusiness. Images have contributed herein development in digital images
taking gadgets, programming or software to work on. The foremost benefit of
digital image analysis is its capacity for objective and non-destructive analysis.
There are tools that may either not only process clear images or also on dark
images to humans like Infrared (IR), ultraviolet (UV) and Near Infrared (NIR). An
image is a two-dimensional representation of a constrained set of digital values is
named a digital image. An image is a 2-D function, f (x, y), where x and y speak to
spatial coordinates, and the adequacy of ‘f’ at any pair of coordinates (x, y) is
known as the grey or intensity level of a given image at that point.

3.2. Digital Image Processing based Applications in Agriculture

Significance and effect of Image processing in society can be decided by its

applications in various fields like aerial and satellite imaging, industrial inspection,
medical imaging, defence applications, law enforcement and agriculture sector.
Various applications of image processing in agriculture area are discussed below.
Digital Image Processing in agricultural applications serves following
purposes:

 For recognition of diseased leaf, fruit as well as stem.

 For thoroughly checking disease prone area.
 For obtaining the shape of affected area through disease.
 For obtaining the colour of disease affected area.
 For finding outsize, variety and shape.

3.3. Application areas of Digital Image processing in agricultural field:

Nutrient inadequacies identification and plant content, Grading quality of fruits,
sorting fruits and inspection, Object tracking, realm and crop estimation, Crop
Management.

3.3.1. Identification of Nutrient inadequacies and plant content:

The lack of large scale (K, N, P, S, Ca and Mg) and small scale (Fe, Mo, Cl, Cu, B,
and Zn) minerals majorly affects plant advancement. Minerals majorly affect plant
advancement. The absence of some supplement minerals particularly of
phosphorus, calcium, iron, and nitrogen is a gigantic issue for agriculture and early
warning and avoidance of the issue will be helpful for agroindustry. Techniques as
of now used to decide nutritional deficiency in plants, plant tissue analysis or
consolidated strategies. Yet, these techniques are moderate and costly.

3.3.2. Fruits quality grading, sorting and inspection:

Agriculture items are reviewed dependent on their measurements and quality. This
evaluation is utilized to sort them and appoint them to various sales channels.
Everything may yield better pay based when appropriately dispensed by its
accurate attributes. Normally, higher evaluation and greater farming items produce
bigger incomes. Conventional evaluating was human dependent. Afterwards,
mechanical gadgets were utilized to separate agrarian items dependent on their
measurements and weight. Classification of fruits and vegetables using feature
extraction and classification models with the different combinations are being
utilized.

3.3.3. Object tracking, land and crop estimation:

Crop of Tobacco territory and yield estimates are significant in balancing out
tobacco costs at the sale floors. The yield of tobacco estimation in Zimbabwe is
presently founded on ground-based and statistical surveys. These strategies are
expensive, tedious, and are inclined to huge mistakes. Remote detecting can give
auspicious data on crop spectral qualities which can be utilized to appraise crop
yields.
3.3.4. Crop Management:
For crop assessment using remote sensing weed detection is used, using pest
management detection of insect has finished and for irrigation also used wireless
sensor network. Phadikar, S. the paper portrays a product model framework for
disease detection of rice dependent on the contaminated images of different plants
of rice. Piyush Chaudhary proposed an algorithm for sickness spot division
utilizing the DIP technique in plant leaf. Yunseop Kim proposed an algorithm for
“wireless sensor networks, software for real-time in-field sensing details of the
instrumentation, software for real-time in-field sensing and design of variable rate
irrigation, and control of a site-specific precision linear-move irrigation system”.
Kamal N. Agrawal proposed the weed identification procedure utilizing an image
processing system.

3.4. Applications based on Imaging Techniques

In image processing source of radiation was important and the sources were
Gamma ray imaging, X-ray imaging, imaging in UV band, imaging in visible
band and IR band, imaging in Microwave band and imaging in Radio band.

In agriculture, Remote Sensing (RS) technique was widely used for various
applications. Remote Sensing was the science of identification of earth
surface features and estimation of geo-biophysical properties using
electromagnetic radiation. Paper reviewed the Rs techniques and its
applications with optical and microwave sensors. Author discussed about the
satellites launched by different countries and their uses in various field along
with spatial, spectral and temporal variations of data. Analytical techniques using
digital image processing, multi-source data fusion and GIS were also discussed.
Applications towards agriculture providing the earth observation data which
supports increased area under agriculture, increased crop intensity and
productivity, etc. RS data can provide the data related to groundwater helping
in irrigation, flood management. Applications like environment assessment and
monitoring, disaster monitoring and mitigation, weather climate, village resource
center, etc. were also discussed.

RS data and pattern recognition technique was used to estimate direct and
independent crop area in the study region. In this review the authors reviewed the
different techniques for crop inventory in Indian scenario. Optical and microwave
data used to classify the crop. Chlorophyll and water were represented by optical
data, crop geometry and dielectric properties were characterized by microwave.
The crop discrimination was carried out using either by visual or digital
interpretation techniques. Visual techniques based on FCC (False Color

Composite) were generated at different bands and were assigned with blue,
green and red colors where as the digital techniques applied to each pixel and use
full dynamic range of observations were preferred for crop discrimination. For

accurate discrimination a multi-temporal approach was used when single date

data fails to do so. Spectral unmixing, direct estimation, crop area estimation,
global estimation using confusion matrix and regression estimator were also
reviewed.
Irrigation was also one of the important parameter in agriculture which was
correlated with the canopy, its reflectance, nutrition etc. Satellite remote sensing
has a lot of potential for routine monitoring of irrigation. The benefits and
drawbacks of remote sensing in crop location, productivity and irrigation setting
were discussed. Authors defined Irrigated lands were the areas that receive full or
partial application of water by artificial means to offset periods of precipitation
shortfalls during the growing period. Spatial scales where the studies of local,
regional and global areas were considered. Local area was related to
command basin, regional to river basins and global to worldwide. Initially hard
copies of satellite images were used to map the irrigated lands at lower costs.
Archival image data from multiple years also proved useful as color changes were
observed between newly and previously irrigated croplands. Digital image
classification techniques for multiple image classification were accurate and useful
as time required for analysis was shorter at lower costs. Commonly used
image classification techniques were multi-stage classification, unsupervised
clustering, density slicing with thresholds, and decision tree classifications.
Normalized Difference Vegetation Index (NDVI) proved to be important for
identifying irrigated areas in local scale studies as it was directly used as input to
classification algorithm. Green index and Relative sensitivity index were
calculated on the basis of reflectance and irrigation.

Thermal imaging and its applications in agriculture were discussed in .

Thermal imaging which was a passive technique (infrared range between 3
to 14 μm) focuses on Water. Water which affects the thermal properties of
plant where leaf contains different amount of water per area can be utilized as an
important parameter in pre harvesting operations. Applications of thermal
imaging to Field nursery, irrigation scheduling, yield forecasting, green houses
termite attack etc were reviewed. Post harvesting operations such as maturity
evaluation, bruise detection, detection of foreign substances in food etc were also
reviewed. Though the thermal imaging produces better results but cannot be
accepted universally in

agriculture applications as the plant physiology and climatic conditions varies

from region to region.

X-ray imaging for luggage inspection of contraband food products, packaged

food specifically bottle or can packed was highly suitable. Ronald P. Haff Æ
Natsuko Toyofuku presented technique of X-ray imaging in detection of defects

and contamination in food. A packaged food (metal, plastic, glass, etc.)

provides much higher contrast in X-ray images than the typical defects or
contaminants of interest that were found in fresh produce (insect infestation,
physiological defects, etc). Poultry inspection for bone fragments and thickness
detection, grain inspection of wheat were few other fields where X-ray imaging
can be utilized. Detection of disease on apple, insect detection in tree nuts and
food grading were few more

applications of X-ray imaging with limitation of high speed inspection. In

food grading also X- ray imaging with classifiers were proved to be effective
sorters.

3.5. Importance of Digital Image Processing in Agriculture:

• Visualization: Observe the items that are not imperceptible.

 • Image Restore and Sharpen: To build up a better image.
• Estimation of Pattern: To estimate the several objects in image
• Image Recognition: Recognize the objects in a picture.
• Image Retrieving: Find ROI in an image.

Conclusion

Digital Image Processing technique manifested as a successful Computer Vision

framework for an agricultural area. Different applications of image processing
have been talked about in detail imaging strategies with various ranges, these
techniques are steady being developed for computerization models and acquiring
higher precision of data. For example, Remote Detecting, Hyper Spectral Infrared
Imaging help decide the vegetation records, cover estimation and so forth with
more accuracy.

Weed classification influences the capitulate (yield)can be effectively categorized

with the algorithms of digital image processing. The classification accuracy ranges
from 85%- 96% relying upon the limitations and algorithms of image acquisition.
So, with these farmers can pertain herbicides in the right structure. The proposed
methodology renders help in protecting the environmental factors. Hence, it can be
conclude that Digital Image-Processing is an effective tool and a non-invasive
method that can be related to the agricultural space with incredible accuracy for
examination of different agronomic variables.

Bibliography

 https://www.researchgate.net/publication/
253908767_Application_of_Image_Processing_in_Agriculture_A_Survey
 https://ceur-ws.org/Vol-3058/Paper-060.pdf
 https://ijarsct.co.in/Paper3178.pdf
 https://en.wikipedia.org/wiki/Digital_image_processing
 https://www.javatpoint.com/dip-image-transformations
 https://www.researchgate.net/figure/Fundamental-steps-of-digital-image-
processing-9_fig1_292336278
 https://neptune.ai/blog/best-image-processing-tools-used-in-machine-
learning
 https://yourtechdiet.com/blogs/best-ai-tools-for-image-processing/
 https://www.analyticsinsight.net/top-10-computer-vision-tools-for-2020/
 https://magnimindacademy.com/blog/image-processing-and-its-future-
implications/
 https://www.design-reuse.com/articles/53213/artificial-intelligence-and-
machine-learning-based-image-processing.html
 https://www.geeksforgeeks.org/digital-image-processing-basics/
 https://www.javatpoint.com/digital-image-processing-tutorial
 https://jivp-eurasipjournals.springeropen.com/articles/10.1186/s13640-018-
0383-6