A

Project Report
On
“Plant Disease Detection System”
Submitted by

Shaikh Saud Abdul Saboor (2021351242028)

Quazi Fahad Arsalan (2021351242022)
Shaikh Shoeb shafique (2021351242025)
Shakeeb Sidique (2021351242039

Submitted in partial fulfillment of requirement for degree of

Bachelor of Technology (Computer Engineering)

Guided by
Mrs. Z. A. Zalte
(Assistant Professor)

Department of Computer Engineering

Hi-Tech Institute of Technology, Chhatrapati. Sambhajinagar
(Academic Year 2022-23)
 CERTIFICATE

This is to certify that, Mr. Shaikh Saud Abdul Saboor, Quazi fahad
Arsalan, Shaikh Shoeb, Siddique Shakeeb has successfully completed
project work entitled “Plant Disease Detection System” in partial fulfillment
for award of Bachelor of Technology(Computer Engineering) Degree of Dr.
Babasaheb Ambedkar Technological University, Lonere Dist. Raigad.

Place : Chhatrapati Sambhajinagar

Date :

Prof. R. A. Zalte Prof. P. M. Mohite

Guide HOD

Examiner Prof. G. S. Dhage

Principal
HIT
Chh. Sambhajinagar

(Academic Year 2022-23)

 CONTENTS

List of Abbreviations i
List of Figures ii
List of Screenshots iii

1. INTRODUCTION 1
1.1 Introduction 1
1.2 Necessity 4
1.3 Objectives 5
1.4 Exisitng system 6
1.5 Proposed system 6
2. LITERATURE SURVEY 8
2.1 Introduction 8
2.2 Deep Learning 9
3. SYSTEM DEVELOPMENT 11
3.1 General Discript ion 11
3.2 Technical Discription 12
3.3 UML Diagram 14
3.4 Sample Code and Output 18
4. PERFORMANCE ANALYSIS 21
4.1 Different Modules of System 21
4.2 Functional Module of System 21
5. CONCLUSION 25
5.1 Conclusion 25
5.2 Future Scope 25
Refrences iv
Acknowledgement v
 List of Abbreviations

1) SVM- Support Vector Machine

2) HOG- histogram of oriented gradients
3) RGB- RED, Blue<Green
4) HSV- Hue Saturation Value
5) HNN- Hopefield Neural Network1

I
 List of figures

Fig. No Fig Name Page. No

Fig. 3.3 System Architecture 12

Fig 3.3.1 Flowchart 13
Fig 3.4.1 Class Diagram 14
Fig 3.4.2 Activity Diagram 15
Fig 3.4.3 Use Case Diagram 16
Fig 3.4.4 Data flow diagram 17

II
 List of Screenshots

Fig. No Fig Name Page. No

Fig. 3.5.1 Tomato Module Code 1 18

Fig 3.5.2 Tomato Module Code 2 19
Fig 3..5.3 Tomato Module Code 3 19
Fig 3.5.4 Healthy Leaf 20
Fig 3.5.5 Infected Leaf 20

III
 1. Introduction

1.1 Introduction
Plant disease detection is an Innovative and Enlightening System helping the
users to know the disease, trainings or any interesting things taking place
around their Area. This Organization aids the native community to keep
themselves up to date about the events around their locality or zone or in their
town. There are 2 things for this method to work; one for the image processing
and another is machine learning. The user is permitted to sight the disease only
ohis town while user can supplement disease connected to any town. Admin
will show if any misuse or inappropriate or false disease added by any users
and will take specific act. The Front end used is Android Studio and backend
as SQL Server. The user has to record into the system to using this app and
can bring up-to-date his details as well. The healthy leaf is shown first and so
on, the user can also restore the disease resultant the latest one shown first and
current disease will be shut. The user can add an image and a title connected to
the leaf. The user can use only 500 words to give a lecture on disease. The
Appearance and texture of evaluation the disease is thrilling and amazing as
the system offers swipe to move to the next or earlier disease with transition
properties. The agriculturist in provincial regions may think that it’s hard to
differentiate the malady which may be available in their harvests. It's not
moderate for them to go to agribusiness office and discover what the infection
may be. Our principal objective is to distinguish the illness introduce in a plant
by watching its morphology by picture handling and machine learning. Pests
and Diseases results in the destruction of crops or part of the plant resulting
indecreased food production leading to food insecurity. Toxic pathogens, poor
disease control, drastic climate changes are one of the key factors which arises
in dwindled food production. Various modern technologies have emerged to
minimize postharvest processing, to fortify agricultural sustainability and to
maximize the productivity. Various Laboratory based approaches such as
polymerase chain reaction, gas chromatography, mass spectrometry,

1
thermography and hyper spectral techniques have been employed for disease
identification. However, these techniques are not cost effective and are high
time consuming. In recent times, server based and mobile based approach for
disease identification has been employed for disease identification. Several
factors of these technologies being high resolution camera, high performance
processing and extensive built in accessories are the added advantages1
resulting in automatic disease recognition. Modern approaches such as
machine learning and deep learning algorithm has been employed to increase
the recognition rate and the accuracy of the results. Various researches have
taken place under the field of machine learning for plant disease detection and
diagnosis, such traditional machine learning approach being random forest,
artificial neural network, support vector machine (SVM), fuzzy logic, K-
means method, Convolution neural networks etc. Random forests are as a
whole, learning method for classification, regression and other tasks that
operate by constructing a forest of the decision trees during the training time.
Unlike decision trees, Random forests overcome the disadvantage of over
fitting of their training data set and it handles both numeric and categorical
data.

The histogram of oriented gradients (HOG) is an element descriptor utilized as

a part of PC vision and image processing for the sake of object detection. Here
we are making utilization of three component descriptors: 1. Hu moments 2.
Harlicka texture 3. Color Histogram Hu moments is basically used to extract
the shape of the leaves. Harlicka texture is used to get the texture of the leaves
and color Histogram is used to represent the distribution of the colors in an
image. The agriculturist in provincial regions may think that it’s hard to
differentiate the malady which may be available in their harvests. It's not
moderate for them to go to agribusiness office and discover what the infection
may be. Our principal objective is to distinguish the illness introduce in a plant
by watching its morphology by picture handling and machine learning. Pests
and Diseases results in the destruction of crops or part of the plant resulting in
decreased food production leading to food insecurity. Also, knowledge about
the pest management or control and diseases are less in various less developed
countries. Toxic pathogens, poor disease control, drastic climate changes are

2
one of the key factors which arises in dwindled food production. Various
modern technologies have emerged to minimize postharvest processing, to
fortify agricultural sustainability and to maximize the productivity. Various
Laboratory based approaches such as polymerase chain reaction, gas
chromatography, mass spectrometry, thermography and hyper spectral
techniques have been employed for disease identification. However, these
techniques are not cost effective and are high time consuming.In recent times,
server based and mobile based approach for disease identification has been
employed for disease identification. Several factors of these technologies
being high resolution camera, high performance processing and extensive built
in accessories are the added advantages resulting in automatic disease
recognition Plant disease detection is a portable system which runs under
automaton stage which is established with native Java language. App will run
smoothly and very fast. Google Material Design is implemented because of
which app looks more attractive and beautiful with good user impression and
experience. Combined with admin and user it manages news, various category,
notification and many things whenever we want. Main preference is good code
with good design. We can save money and time by using this app and we can
create our own design and special apps or different kind of app based on our
requirements. Plant disease detection is an Innovative and Enlightening
System helping the users to know the disease, trainings or any interesting
things taking place around their Area. This Organization aids the native
community to keep themselves up to date about the events around their
locality or zone or in their town. There are 2 things for this method to work;
one for the image processing and another is machine learning. The user is
permitted to sight the disease only of his town while user can supplement
disease connected to any town. Admin will show if any misuse or
inappropriate or false disease added by any users and will take specific act.
The Front end used is Android Studio and backend as SQL Server. The user
has to record into the system to using this app and can bring up-to-date his
details as well. The healthy leaf is shown first and so on, the user can also
restore the disease resultant the latest one shown first and current disease will
be shut. The user can add an image and a title connected to the leaf.

3
1.2 Necessity
In this changing environment, appropriate and timely disease identification
including early prevention has never been more important. There are several
ways to detect plant pathologies. Some diseases do not have any visible
symptoms, or the effect becomes noticeable too late to act, and in those
situations, a sophisticated analysis is obligatory. However, most diseases
generate some kind of manifestation in the visible spectrum, so the naked eye
examination of a trained professional is the prime technique adopted in
practice for plant disease detection. In order to achieve accurate plant disease
diagnostics a plant pathologist should possess good observation skills so that
one can identify characteristic symptoms to find out whether the leaf is
diseased or healthy, certain steps must be followed. i.e., Preprocessing,
Feature extraction, Training of classifier and Classification. Preprocessing of
image, is bringing all the images size to a reduced uniform size. Then comes
extracting features of a preprocessed image which is done with the help of
HOG .Hog is a feature descriptor used for object detection. In this feature
descriptor the appearance of the object and the outline of the image is
described by its intensity gradients. One of the advantages of Hog feature
extraction is that it operates on the cells created. Any transformations don’t
affect this. Augmentation Process.: The main purpose of applying
augmentation is to increase the dataset and introduce slight distortion to the
images which helps in reducing overfitting during the training stage. In
machine learning, as well as in statistics, overfitting appears when a statistical
model describes random noise or error rather than underlying relationship. The
image augmentation contained one of several transformation techniques
including affine transformation, perspective transformation, and simple image
rotations Affine transformations were applied to express translations and
rotations (linear transformations and vector addition, resp.) where all parallel
lines in the original image are still parallel in the output image. To find a trans-
formation matrix, three points from the original image were needed as well as
their corresponding locations in the output image. For perspective
transformation, a 3×3transformation matrix was required. Straight lines would
remain straight even after the transformation. For the augmentation process,
simple image rotations were applied, as well as rotations on the different axis

4
by various degrees. Hu moments: Image moments which have the important
characteristics of the image pixels helps in describing the objects. Here Hu
moments help in describing the outline of a particular leaf. Hu moments are
calculated over single channel only. The first step involves converting RGB to
Gray scale and then the Hu moments are calculated. This step gives an array
of shape descriptors. Harlicka Texture: Usually the healthy leaves and
diseased leaves have different textures. Here we use Harlicka texture feature to
distinguish between the textures of healthy and diseased leaf. It is based on the
adjacency matrix which stores the position of (I, J). Texture is calculated
based on the frequency of the pixel I occupying the position next to pixel J. To
calculate Harlicka texture, it is required that the image be converted to gray
scale. Color Histogram: Color histogram gives the representation of the colors
in the image. RGB is first converted to HSV color space and the histogram is
calculated for the same. It is needed to convert the RGB image to HSV since
HSV model aligns closely with how human eye discerns the colors in an
image. Histogram plot provides the description about the number of pixels
available in the given color range

1.3 Objectives
Modern approaches such as machine learning and deep learning algorithm has
been employed to increase the recognition rate and the accuracy of the results.
Random forests are as a whole, learning method for classification, regression
and other tasks that operate by constructing a forest of the decision trees
during the training time. Unlike decision trees, Random forests overcome the
disadvantage of over fitting of their training data set and it handles both
numeric and categorical data. The histogram of oriented gradients (HOG) is an
element descriptor utilized as a part of PC vision and image processing for the
sake of object detection Here we are making utilization of three component
descriptors:
1. Hu moments
2. Harlicka texture
3. Color Histogram

5
1.4 Existing System (Limitations)
The problem of efficient plant disease protection is closely related to the
problems of sustainable agriculture and climate change. Research results
indicate that climate change can alter stages and rates of pathogen
development; it can also modify host resistance, which leads to physiological
changes of host-pathogen interactions. The situation is further complicated by
the fact that, today, diseases are transferred globally more easily than ever
before. New diseases can occur in places where they were previously
unidentified and, inherently, where there is no local expertise to combat them.
Timely and accurate diagnosis of plant diseases is one of the pillars of
precision agriculture.

1.5 Proposed System (Advantages)

To find out whether the leaf is diseased or healthy, certain steps must be
followed. i.e., Preprocessing, Feature extraction, Training of classifier and
Classification. Preprocessing of image, is bringing all the images size to a
reduced uniform size. Then comes extracting features of a preprocessed image
which is done with the help of HOG .Hog is a feature descriptor used for
object detection. In this feature descriptor the appearance of the object and the
outline of the image is described by its intensity gradients. One of the
advantages of Hog feature extraction is that it operates on the cells created.
Any transformations don’t affect this. Here we made use of three feature
descriptors. Hu moments: Image moments which have the important
characteristics of the image pixels helps in describing the objects. Here Hu
moments help in describing the outline of a particular leaf. Hu moments are
calculated over single channel only. The first step involves converting RGB to
Gray scale and then the Hu moments are calculated. This step gives an array
of shape descriptors. Harlicka Texture: Usually the healthy leaves and
diseased leaves have different textures. Here we use Harlicka texture feature to
distinguish between the textures of healthy and diseased leaf. It is based on the
adjacency matrix which stores the position of (I, J). Texture is calculated
based on the frequency of the pixel I occupying the position next to pixel J. To
calculate Harlicka texture, it is required that the image be converted to gray
scale. Color Histogram: Color histogram gives the representation of the colors

6
in the image. RGB is first converted to HSV color space and the histogram is
calculated for the same. It is needed to convert the RGB image to HSV since
HSV model aligns closely with how human eye discerns the colors in an
image. Histogram plot provides the description about the number of pixels
available in the given color range.

7
 2. Literature Survey

2.1 Introduction
In 2015, S. Khirade et Al. tackled the problem of plant disease detection using
digital image processing techniques and back propagation neural network
(BPNN) [1]. Authors have elaborated different techniques for the detection of
plant disease using the images of leaves. They have implemented Otsu’s
thresholding followed by boundary detection and spot detection algorithm to
segment the infected part in leaf. After that they have extracted the features
such as color, texture, morphology, edges etc. for cla ssification of plant
disease. BPNN is used for classification i.e. to detect the plant disease.
Shiroop Madiwalar and Medha Wyawahare analyzed different image
processing approaches for plant disease detection in their research [2]. Authors
analyzed the color and texture features for the detection of plant disease. They
have experimented their algorit hms on the dataset of 110 RGB images. The
features extracted for classification were mean and standard deviation of RGB
and YCbCr channels, grey level cooccurrence matrix (GLCM) features, the
mean and standard deviation of the image convolved with Gabor f ilter.
Support vector machine classifier was used for classification. Authors
concluded that GCLM features are effective to detect normal leaves. Whereas
color features and Gabor filter features are considered as best for detecting
anthracnose affected lea ves and leaf spot respectively. They have achieved
highest accuracy of 83.34% using all the extracted features. Peyman
Moghadam et Al. demonstrated the application of hyperspectral imaging in
plant disease detection task [3]. visible and nearinfrared (VNI R) and short
infrared (SWIR) spectrums were used in this research. Authors have used k--
wave means clustering algorithm in spectral domain for the segmentation of
leaf. They have proposed a novel grid removal algorithm to remove the grid
from hyperspectral images. Authors have achieved the accuracy of 83% with
vegetation indices in VNIR spectral range and 93% accuracy with full
spectrum. Though the proposed method achieved higher accuracy, it requires
the hyperspectral camera with 324 spectral bands so the s olution becomes too

8
costly. Sharath D. M. et Al. developed the Bacterial Blight detection system
for Pomegranate plant by using features such as color, mean, homogeneity, SD,
variance, correlation, entropy, edges etc. Authors have implemented grab cut
segm entation for segmenting the region of interest in the image [4]. Canny
edge detector was used to extract the edges from the images. Authors have
successfully developed a system which can predict the infection level in the
fruit. Garima Shrestha et Al. depl oyed the convolutional neural network to
detect the plant disease [5]. Authors have successfully classified 12 plant
diseases with 88.80% accuracy. The dataset of 3000 high resolution RGB
images were used for experimentation. The network has 3 blocks of co
nvolution and pooling layers. This makes the network computationally
expensive. Also the F1 score of the model is 0.12 which is very low because
of higher number of false negative predictions.

2.2 Deep Learning

Deep learning is probably one of the hottest tech topics right now. Large
corporations and young startups alike are all gold-rushing this fancy field. If
you think big data is important, then you should care about deep learning. says
that in the 21st Century. If data is the crude oil, databases and data warehouses
are the drilling rigs that digs and pumps the data on the internet, then think of
deep learning as the oil refinery that finally turns crude oil into all the useful
and insightful final products. There could be a lot of “fossil fuels” hidden
underground, and there are a lot of drills and pumps in the market, but without
the right refinery tools, you ain’t gonna get anything valuable. That’s why
deep learning is important. It’s part of the data-driven big picture.The good
news is, we are not going to run out of data and our “refinery machine” is
getting better and better. Today, just about doing anything online will generate
data. So data, unlike oil, is “sustainable” and growing “explosively”. In the
meantime, as long as the data isn’t garbage-in, then there’s no garbage-out
from deep learning. Hence the more data, the merrier. is improving on both
software and hardware. Deep learning algorithms have improved over the past
few decades and developers around the world have contributed to open-source
frameworks like TensorFlow, Theano, Keras, and Torch, all of which make it
easy for people to build deep learning algorithms as if playing with LEGO

9
pieces. And thanks to the demand from gamers around the world, GPUs
(graphics processing units) make it possible for us to leverage deep learning
algorithms to build and train models with impressive results in a timeefficient
manner! So to all the parents who don’t like your kids playing games: Gaming
has its silver Living.

10
 3. System Development

3.1 General Description of the System

Augmentation Process: The main purpose of applying augmentation is to
increase the dataset and introduce slight distortion to the images which helps
in reducing overfitting during the training stage. The image augmentation
contained one of several transformation techniques including affine trans-
formation, perspective transformation, and simple image rotations.Affine
transformations were applied to express translations and rotations where all
parallel lines in the original image are still parallel in the output image. To
find a trans-formation matrix, three points from the original image were
needed as well as their corresponding locations in the output image. Straight
lines would remain straight even after the transformation. For the
augmentation process, simple image rotations were applied, as well as
rotations on the different axis by various degrees. In software engineering, a
functional requirement defines a function of a software system or its
component. A function is described as a set of inputs, the behavior, and
outputs. Functional requirements may be calculations, technical details, data
manipulation and processing and other specific functionality that define what a
system is supposed to accomplish. Here, the system has to perform the
following tasks Here first of all a simple data will be taken in the form
of .excel or .csv extension. After taking it, data cleaning will be done which is
called as preprocessing which means any type of process performed on raw
data to prepare it for another processing procedure. Then visualization will
take place in which means the representation of an object, situation or set of
information as a chart or other image(leaf). Then finally the predicted output
will come.

3.2 Technical Requirement of the System

Hardware Requirements
Processor: Any Processor
RAM: more than 2GB
Hard Disk: 10 GB

11
 Input device: Standard Keyboard and Mouse
Output device: High Resolution Monitor
Memory: 1GB RAM1
Different plant leaf images (healthy and affected)
Software Requirements
Operating system: Android 9 and upper
IDE: Python IDLE
Data: Leaf Dataset
Modules: NumPy, pandas, matplotlib, sklearn
Processor: snapdragon pr any standard processor

3.3 System Architecture

Input Leaf Image Pre Processing Feature Extraction

Database Images Training Images NN Classification

Abnormal Normal

Defined Region
Classified

Fig3.3 : System Architecture

12
Flow Chart

Image Acquisition

Image Pre Processing

Image Segmentation

Feature extraction in image

Detection and classification of

plant Disease

Fig3.3.1: Flow chart

13
3.4 UML and Data flow Diagram

Fig3.4.1 : Class Diagram

14
Activity Diagram

Fig 3.4.2: Activity Diagram

15
Use Case Diagram

Fig 3.4.3: Use Case Diagram

16
Data Flow Diagram

Fig 3.4.5: Data flow Diagram

17
3.5 Sample Code and Output

Sample Code

Fig 3.5.1 : Tomato Module Code 1

18
Fig 3.5.2 : Tomato Module Code 2

Fig 3.5.3 : Tomato Module Code 3

19
Output Screenshots

Fig 3.5.4 :Healthy Leaf

Fig 3.5.5 : Infected Leaf

20
 4. Performance Analysis

4.1 Different Modules of the System

This process consists two main steps:
1) Image processing
2) Machine learning algorithm

4.2 Functional Description of Modules

1)Image Processing: It is used by some researchers for detection
andclassification of wheat leaf disease. The steps of leaf diseases detection and
classification are given below:
1. Image acquisition.
The first stage of any vision system is the image acquisition stage. After the
image has been
obtained, various methods of processing can be applied to the image to
perform the many different vision tasks required today. However, if the image
has not been acquired satisfactorily then the intended tasks may not be
achievable, even with the aid of some form of image enhancement.
2. Preprocessing.
Image processing is a method to convert an image into digital form and
perform some operations on it, in order to get an enhanced image or to
extractsome useful information from it. It is a type of signal dispensation in
which input is image, like video frame or photograph and output may be
image or characteristics associated with that image. Usually, Image Processing
system includes treating images as two-dimensional signals while applying
already set signal processing methods to them. It is among rapidly growing
technologies today, with its applications in various aspects of a business.
Image Processing forms core research area within engineering and computer
science disciplines too. Image processing basically includes the following
three steps:
• Importing the image with optical scanner or by digital photography.

21
• Analyzing and manipulating the image which includes data compression and
image enhancement and spotting patterns that are not to human eyes like
satellite photographs. Output is the last stage in which result can be altered
image or report that is based on image analysis.

3. Segmentation of infected regions.

Image segmentation is the process of partitioning a digital image into multiple
segments (sets of pixels, also known as super-pixels). The goal of
segmentation is to simplify and/or change the representation of an image into
something that is more meaningful and easier to analyze. Image segmentation
is typically used to locate objects and boundaries (lines, curves, etc.) in images.
More precisely, image segmentation is the process of assigning a label to
every pixel in an image such that pixels with the same label share certain
characteristics. The result of image segmentation is a set of segments that
collectively cover the entire image, or a set of contours extracted from the
image. Each of the pixels in a region are similar with respect to some
characteristic or computed property, such as color, intensity, or texture.
Adjacent regions are significantly different with respect to the same
characteristic(s).

4. Feature extraction
In machine learning, pattern recognition and in image processing, feature
extraction starts from an initial set of measured data and builds derived values
(features) intended to be informative and non-redundant, facilitating the
subsequent learning and generalization steps, and in some cases leading to
better human interpretations. Feature extraction is a dimensionality reduction
process, where an initial set of raw variables is reduced to more manageable
groups (features) for processing, while still accurately and completely
describing the original data set. When the input data to an algorithm is too
large to be processed and it is suspected to be redundant (e.g., the same
measurement in both feet and meters, or the repetitiveness of images presented
as pixels), then it can be transformed into a reduced set of features (also
named a feature vector). Determining a subset of the initial features is called
feature selection. The selected features are expected to contain the relevant

22
information from the input data, so that the desired task can be performed by
using this reduced representation instead of the complete initial data.

5. Feature selection
In machine learning and statistics, feature selection, also known as variable
selection, attribute selection or variable subset selection, is the process of
selecting a subset of relevant features (variables, predictors) for use in model
construction.
Feature selection techniques are used for four reasons:
• simplification of models to make them easier to interpret by
researchers/users,
• shorter training times,
• to avoid the curse of dimensionality,
• enhanced generalization by reducing overfitting (formally, reduction of
variance

1) Machine Learning Algorithm

SUPPORT VECTOR MACHINE(SVM)- They were extremely popular
around the time they were developed in the 1990s and continue to be the go-to
method for a high-performing algorithm with little tuning. In machine learning,
support vector machine is a set of supervised learning models with associated
learning algorithms that analyses data used for Classification and regression
analysis. When data are not labeled supervised learning is not possible. It
constructs a hyper lane and a set of hyper lanes which in a high and infinite
dimensional space, which can be used for other task like outlier detection.
NEURAL NETWORKS The disease detection techniques are based on two
main neural network technologies: Self-Organizing map and multilayer
perceptron (the most widely used architecture). Neural network is a system of
hardware and/or software patterned after the operation of neurons in the
human brain. Neural network also called artificial neural network. RANDOM
FOREST CLASSIFIER Random forests or random decision forests are an
ensemble learning method for classification, regression and other tasks that
operates by constructing a multitude of decision trees at training time and
outputting the class that is the

23
mode of the classes (classification) or mean prediction (regression) of the
individual trees. Random decision forests correct for decision trees' habit of
over fitting to their training set. Random forest classifier creates a set of
decision trees from randomly selected subset of training set. It then aggregates
the votes from different decision trees to decide the final class of the test
object.

HOG (Histogram of Oriented Gradients)- The histogram of oriented gradients

(HOG) is a feature descriptor used in computer vision and image processing
for the purpose of object detection. The technique counts occurrences of
gradient orientation in localized portions of an image. This method is similar
to that of edge orientation histograms, scale-invariant feature transform
descriptors, and shape contexts, but differs in that it is computed on a dense
grid of uniformly spaced cells and uses overlapping local contrast
normalization for improved accuracy. Hog is a feature descriptor used for
object detection. In this feature descriptor the appearance of the object and the
outline of the image is described by its intensity gradients. One of the
advantages of Hog feature extraction is that it operates on the cells created.
Any transformation doesn’t affect this.

24
 5. Conclusion

5.1 Conclusion
The main aim of our project is to detect whether it is diseased or healthy leaf
with the help of a Random Forest classifier. The objective of this algorithm is
to recognize abnormalities that occur on plants in their greenhouses or natural
environment. The image captured is usually taken with a plain background to
eliminate occlusion. The algorithm was contrasted with other machine
learning models for accuracy. Using Random Forest classifier, the model was
trained using 160 images of papaya leaves. The model could classify with
approximate 70 percent accuracy. The accuracy can be increased when trained
with vast number of images and by using other local features together with the
global features such as SIFT (Scale Invariant Feature Transform), SURF
(Speed Up Robust Features) and DENSE along with BOVW (Bag of Visual
Word). There are many methods in automated or computer vision plant
disease detection and classification process, but still, this research field is
lacking. In addition, there are still no commercial solutions on the market,
except those dealing with plant species recognition based on the leaf's images.

5.2 Future Scope

Future enhancement for this project is to implement a cloud storage in order to
consists of the results of plant disease defect detection which has to be sent to
the farmers so as to they can use the right fertilizers for that particular disease.

Cloud
Cloud storage is a service which lets you store data by transferring it over the
Internet or another network to an offsite storage system maintained by a third
party. There are hundreds of different cloud storage systems which include
personal storage which holds and/or backs up emails, pictures, videos and
other personal files of an individual, to enterprise storage which lets
businesses use cloud storage as a commercially-supported remote backup
solution where the company can securely transfer and store data files or share
them between.

25
Drones
Drone photography allows images and audio/video to be captured that might
not be otherwise possible for human photographers and
videographers.capacity can be enabled by the flight abilities of drones, their
small size or their ability to tolerate harsh environments.

26
 References

[1] Ghaiwat Savita N, Arora Parul. Detection and classification of plant leaf diseases
using image processing techniques: a review. Int J Recent Adv Eng Technol
2014;2(3):2347– 812. ISSN (Online).
[2] Dhaygude Sanjay B, Kumbhar Nitin P. Agricultural plant leaf disease detection
using image processing. Int J Adv Res Electr Electron Instrum Eng 2013;2(1).
[3] Mrunalini R Badnakhe, Deshmukh Prashant R. An application of K-means
clustering and artificial intelligence in pattern recognition for crop diseases. Int Conf
Adv Inf Technol 2011;20. 2011 IPCSIT.
[4] Arivazhagan S, Newlin Shebiah R, Ananthi S, Vishnu Varthini S. Detection of
unhealthy region of plant leaves and classification of plant leaf diseases using texture
features. Agric Eng Int CIGR 2013;15(1):211–7.
[5] Kulkarni Anand H, Ashwin Patil RK. Applying image processing technique to
detect plant diseases. Int J Mod Eng Res 2012;2(5):3661–4.
[6] Bashir Sabah, Sharma Navdeep. Remote area plant disease detection using image
processing. IOSR J Electron Commun Eng 2012;2(6):31–4. ISSN: 2278-2834.
[7] Naikwadi Smita, Amoda Niket. Advances in image processing for detection of
plant diseases. Int J Appl Innov Eng Manage 2013;2(11). Patil Sanjay B et al. Leaf
disease severity measurement using image processing. Int J Eng Technol
2011;3(5):297–301.
[8] Chaudhary Piyush et al. Color transform-based approach for disease spot
detection on plant leaf. Int Comput Sci Telecommun 2012;3

IV
 Acknowledgement

Ability & ambition are not enough for success. Success in any endeavor
depends a lot on the support, guidance, encouragement from our guides,
friends & our closer to perfection has helped us to motivate ourselves into
giving the best in our means. Gratitude is often the hardest emotion to express
& often one doesn’t find adequate words to convey what one feels.

We would like to place on record our deep sense of gratitude to Prof. P. M.

Mohite, HOD-Dept. of Computer Science and Engineering, for their generous
guidance, help and useful suggestions. We express our sincere gratitude to
Guide Prof. Z. A. Zalte for her stimulating guidance, continuous
encouragement and supervision throughout the course of present work. We are
pleased to express our deep sense of gratitude to our project in-charge Prof.
K.P. Ingale who is supporting us during the entire course of our project
extending her continuous co-operation & encouragement. We extremely
thankful to Prof. G. S. Dhage, Principal, Hi-Tech Institute of Technology,
Chhatrapati Sambhajinagar, for providing us infrastructural facilities to work
in, without which this work would not have been possible. Last but not the
least, a great deal of appreciation & best wishes to all friends for their
contribution & encouragement during this work.

Shaikh Saud Abdul Saboor

Quazi Fahad Arsalan
Shaikh Shoeb Shafique
Shakeeb Siddique

V
VI