Project Report on

Citrus Plant Disease Classifcation and

Recommendation System Using Deep Learning

Submitted in complete fulllment of the requirements for the Degree of

Bachelor of Engineering In Information Technology

by
Rakhunde Pranav (B190358564) Sawant Sourabh(B190358566)
Yadav Sanket (B190358580) Sawant Yash(B190358581)

Under the guidance of

Mr. B. S. Salve
Department of Information Technology
Vidya Pratishthan’s
Kamalnayan Bajaj Institute of Engineering and Technology
Baramati-413133, Dist-Pune (M.S.)
India
May 2023
 VPKBIET, Baramati

Certificate
This is to certify that the project report on
Citrus Plant Disease Classifcation and
Recommendation System Using Deep Learning
submitted by
Rakhunde Pranav (B190358564) Sawant Sourabh (B190358566)
Yadav Sanket(B190358580) Sawant Yash(B190358581)
in the completely fulfillment of the requirement for the award of
Degree of Bachelor of Engineering in Information Technology at Vidya
Pratishthan’s Kamalnayan Bajaj Institute Of Engineering and
Technology, Baramati under the Savitribai Phule Pune University,
Pune. This work is done during year 2022-23 Sem-II, under our guidance.

Mr. B. S. Salve Dr. S. A. Takale Dr. R. S. Bichkar

Project Guide Head of Dept. Principal

Examiner 1:- - - - - - - Examiner 2: - - - - - - -

i
Acknowledgements

I feel happy in forwarding this seminar report as an image of sincere eort. The successful
project reects my work, eort of my guide in giving me good information. I express my
deep gratitude to all sta members who lend me their valuable support and cooperation
to enable me to complete my seminar successfully. My sincere thanks to my guide
Mr. B. S. Salve sir who has been constant source of inspiration and guiding star in
achieving my goal. I give my special thanks to respected Prof. P.M.Patil sir who is
Project coordinator and Dr. S.A.Takale ,Head of Information Technology department
for their constant interest and encouragement throughout the completion of our project.
I am also equally indebted to our principal Dr.R.S.Bichkar sir for his valuable help
whenever needed.
Thank You!

Pranav Rakhunde

Sourabh Sawant

Sanket Yadav

Yash Sawant

1
Abstract

Nowadays, with the development in machine learning and deep learning, it is possible to
not only identify but control plant diseases by using computer devices instead of manual
inspection. So it helped in improving the quality as well as production of fruits. Citrus
fruits are well known for their taste and nutritional value. They are one of the natural
and well-known sources of vitamin C, so planted worldwide. Manual inspection of fruit
diseases with the naked eye takes time and also it is dicult. Therefore, a computer-
based method is always required for the accurate recognition of plant diseases. So build
a citrus image dataset including all common citrus diseases.
The deep learning network is used to train and learn these images, Which can ef-
fectively identify and classify plant diseases. The CNN model is used as the primary
network. The results show that techniques of data augmentation and preprocessing have
delivered promising insights to estimate citrus fruit’s damages in percentage and also
identify and classify agricultural diseases with relevant suggestions through which can
avoid citrus plant disease with specic insecticides, Pesticides, and fertilizers.

2
Contents

Acknowledgements 1

Abstract 2

Keywords 7

Notation and Abbreviations 8

1 Introduction 9
1.1 Introduction . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 9
1.2 Motivation . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 10

2 Literature Survey 11

3 Proposed Work 15
3.1 Problem Denition . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 15
3.2 Scope of Project . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 15
3.3 Project Objectives . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 16
3.4 Project Constraints . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 16

4 Project Requirement Specication 17

4.1 Performance Requirements . . . . . . . . . . . . . . . . . . . . . . . . . . 17
4.2 Software Quality Attributes/Requirements . . . . . . . . . . . . . . . . . 17
4.3 Security Requirements . . . . . . . . . . . . . . . . . . . . . . . . . . . . 18
4.4 Hardware Requirements . . . . . . . . . . . . . . . . . . . . . . . . . . . 18
4.5 Software Requirements . . . . . . . . . . . . . . . . . . . . . . . . . . . . 18

5 Systems Architecture 19

6 Project Planning 21
6.1 Project Estimates . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 21
6.2 Team Structure . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 24

7 Project Schedule 25
7.1 Project Breakdown Structure . . . . . . . . . . . . . . . . . . . . . . . . 25
7.2 Task Network . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 26

3
CONTENTS CONTENTS

7.3 Time-line charts . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 27

8 Project Design 28
8.1 DataFlow Levels . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 28
8.1.1 Dataow Level 0 . . . . . . . . . . . . . . . . . . . . . . . . . . . 28
8.1.2 Dataow Level 1 . . . . . . . . . . . . . . . . . . . . . . . . . . . 29
8.1.3 Dataow Level 2 . . . . . . . . . . . . . . . . . . . . . . . . . . . 30
8.2 UML Diagrams . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 31
8.3 Usecase Diagram . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 31
8.4 Activity Diagram . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 32
8.5 Class Diagram . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 33

9 System Algorithms and Implementation 34

9.1 Dataset Descriptions . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 34
9.2 CNN Algorithm . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 35
9.2.1 Algorithm Steps . . . . . . . . . . . . . . . . . . . . . . . . . . . 35
9.3 Code . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 36

10 Test Cases 40

11 Experimental Results 42
11.1 GUI . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 42
11.1.1 Load Image Module . . . . . . . . . . . . . . . . . . . . . . . . . . 42
11.1.2 Process Module . . . . . . . . . . . . . . . . . . . . . . . . . . . . 43
11.1.3 Output Module . . . . . . . . . . . . . . . . . . . . . . . . . . . . 44
11.2 Working Modules . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 45
11.2.1 Disease Detection . . . . . . . . . . . . . . . . . . . . . . . . . . . 45
11.2.2 Recommendation based on diseases . . . . . . . . . . . . . . . . . 45
11.3 Experimental Results and Discussions . . . . . . . . . . . . . . . . . . . . 46
11.3.1 Confusion Matrix . . . . . . . . . . . . . . . . . . . . . . . . . . . 46
11.3.2 Precision, Recall and F1 Score . . . . . . . . . . . . . . . . . . . . 46
11.3.3 Accuracy . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 47
11.3.4 Loss . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 47

12 Conclusion and Future Scope 48

12.1 Conclusion . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 48
12.2 Future Scope . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 49

References 50

A Appendix 51

B Base Paper 52

C Tools Used 53

D Papers Published/Certicates 54

4
List of Figures

5
List of Figures

4.1 System Architecture ......................................................................... 16

7.1 Project Breakdown Structure ............................................................... 23
7.2 Task Network ........................................................................................ 24
7.3 Time Line Chart ................................................................................... 25
8.1.1 Data Flow Diagram (DFD)- 0 ............................................................ 26
8.1.2 Data Flow Diagram (DFD)- 1 ............................................................ 27
8.1.3 Data Flow Diagram (DFD)- 2 ............................................................ 28
8.1 Usecase Diagram ................................................................................... 29
8.2 Activity Diagram ................................................................................... 30
8.3 Class Diagram ........................................................................................ 31
8.4 Architectural Design .............................................................................. 32
10.1 GUI ....................................................................................................... 41
10.3 Model Accuracy’s .................................................................................. 43
10.4 CNN Model recall for each class ........................................................... 44
10.5 CNN Model precision for each class ...................................................... 45

6
Keywords

List of keywords -

• Deep Learning

• Convolutional Neural Network

• Image Classication

• Feature Selection

• Data Augumentation

• Whale Optimization Algorithm

7
Notation and Abbreviations

List of Notations -

• API: Application Programming Interface

• CNN: Convolutional Neural Network

• DFD: Data Flow Diagram

• GUI: Graphical User Interface

• HDD: Hard Disk Drive

• SSD: Solid State Drive

• UML: Unied Modelling Language

• WOA: Whale Optimization Algorithm

8
Chapter 1

Introduction

1.1 Introduction

There are many types of agricultural calamities with great impact and frequent disasters,
which not only cause losses to crop production but also threaten food safety. Crop disease
is one of the main types of “disasters” which aect the citrus plant. Citrus disease is one
of the most important trading crops all over the world. It brings great economic losses to
farmers. There are some diseases that are such as Greening, Canker, Scab, Black spot,
and Melanose. It takes selects several common citrus diseases as experimental objects
disease problems certainly aect crops throughout their growing cycle.
In the agriculture eld, disease detection is an important step. If the disease is not
detected at an early stage will lead to farmers’ economic loss. Machine vision framework
uses image processing techniques to perform such specic work, which is why image pro-
cessing assumes an exceptionally signicant job in their capabilities. The system will
take input as images of citrus plant and gives output as detected diseases for which plant
is infected and provide the recommendation by proving required measurements of fertil-
izers or pesticides through CNN and classication algorithms. So the system is proposed
to classify the diseases using Convolutional Neural Network.

9
1.2. MOTIVATION CHAPTER 1. INTRODUCTION

1.2 Motivation

The main motivation behind this project is that it Proposed CNN-based citrus plant
disease identication model is capable of distinguishing between healthy and diseased
citrus fruits and leaves. We used the CNN model to tackle the problem of classifying
diseases from citrus fruit and leaf images in this study. The modules in our proposed
model are as follows: i) Data loading, ii) Data preprocessing, and iii) building CNN
model. Collects high-level attributes, yielding disease classication of citrus fruit/leaves
into Black spot, Canker, Scab, Greening which not the human eye can’t see. It also not
only detects the disease but also predicts the required fertilizers by which it prevents the
disease the increase the citrus yielding.

Citrus Plant Disease Classifcation and 10 VPKBIET, Baramati

Recommendation System Using Deep Learning
Chapter 2

Literature Survey

1. Muhammad Hassam, Muhammad Attique Khan, Ammar Armghan, Sara

A Althubiti, Majed Alhaisoni, Abdullah Alqahtani,Seifedine Kadry, Yong-
sung Kim, ”A Single Stream Modied MobileNet V2 and Whale controlled
Entropy based Optimization Framework for Citrus Fruit Diseases Recogni-
tion”, IEEE Access, 2022, doi: 10.1109/ACCESS.2022.3201338

This system used computer vision as well as deep learning algorithms such as Convolu-
tional Neural Network, Pretrained Mobile Net-V2, Whale Optimization for optimization
of the features. Firstly, data of images citrus was augmented. Later on, It was trained
by using pre-trained network Mobile Net V2 CNN and ne-tuned. The newly trained
model was used for deep feature extraction. After that used Whale Optimization algo-
rithm (WOA) to remove redundant information present in the features. Lastly, images
were classied into dierent kinds of diseases.
Technique Used:

• Mobile Net V2

• Data Augmentation

• CNN

• Whale Optimization Algorithm

11
 CHAPTER 2. LITERATURE SURVEY

2. Vinay Kukreja, Poonam Dhiman, ”A Deep Neural Network based disease

detection scheme for Citrus fruits, ”IEEE Xplore Part Number: CFP20V90-
ART; ISBN: 978-1-7281-5461-9

In this system Deep learning algorithms have been implemented for citrus disease
detection to classify fruit into healthy and defective classes. First, a dense CNN model
was used without performing preprocessing and data augmentation on 150 frames and
achieved an accuracy of 67 percent, But the proposed model used data augmentation
and preprocessing to improve CNN performance and used 1200 frames. Furthermore,
the proposed model is compared with a dense model where data augmentation and
preprocessing techniques were not used. The overall accuracy of the proposed model is
89.1 percent. The results show that the data augmentation and preprocessing techniques
yielded promising insights for damage estimation of citrus fruits.
Technique Used:

• Convolutional Neural Network

• Data Augmentation

• Image Processing

Citrus Plant Disease Classifcation and 12 VPKBIET, Baramati

Recommendation System Using Deep Learning
 CHAPTER 2. LITERATURE SURVEY

3. Wenyan Pan, Jiaohua Qin,Xuyu Xiang, Yan Wu1, Yun Tan, and Lingyun
Xiang, ”A Smart Mobile Diagnosis System for Citrus Diseases Based on
Densely Connected Convolutional Networks”, date of publication June 26,
2019; date of current version July 18, 2019. Digital Object Identier 10.1109/AC-
CESS.2019.2924973

In this system, they had taken image dataset of six types of citrus diseases and made a
intelligent diagnostic system for citrus diseases by creating a simplied densely networked
convolutional networks (DenseNet). The system is implemented using the WeChat applet
on a mobile device, through which users can upload images and receive diagnostic results
and comments. Experimental results showed that citrus disease recognition accuracy
exceeds 88 percent. Also, prediction time had decreased due to use of DenseNet structure.
Technique Used:

• Dense-Net

• Intelligent diagnosis

• WeChat applet

• Mobile device computing

Citrus Plant Disease Classifcation and 13 VPKBIET, Baramati

Recommendation System Using Deep Learning
 CHAPTER 2. LITERATURE SURVEY

4.Muhammad Zia Ur Rehman , Fawad Ahmed, Muhammad Attique Khan,

Usman Tariq,Sajjad Shaukat Jamal , Jawad Ahmad , and Iqtadar Hussain
, ”A Single Stream Modied MobileNet V2 and Whale controlled Entropy
based Optimization Framework for Citrus Fruit Diseases RecognitionClassi-
cation of Citrus Plant Diseases Using Deep Transfer Learning ”,” Computers,
Materials Continua Tech Science Press DOI:10.32604/cmc.2022.0190

In this system, a new deep learning-based technique for citrus disease classication is
proposed. In this work,two dierent pre-trained deep learning models were used. Image
scaling techniques are used to increase the size of the citrus dataset used in this paper. In
addition, hybrid contrast stretching was used to improve the visual quality of the images.
In addition, transfer learning is used to retrain pre-trained models, and the feature set is
enriched with the use of fusion. The merged feature set is optimized using a metaheuristic
algorithm, the Whale Optimization Algorithm (WOA). The selected characters are used
to classify six dierent diseases of citrus plants. The proposed technique achieves a
classication accuracy of 95.7 percent with excellent results compared to state-of-the-art
techniques.
Technique Used:

• Mobile Net V2

• CNN

• Whale Optimization Algorithm (WOA)

• Data Augmentation

• Dense Net

• Transfer Learning

Citrus Plant Disease Classifcation and 14 VPKBIET, Baramati

Recommendation System Using Deep Learning
Chapter 3

Proposed Work

3.1 Problem Denition

In agriculture eld, disease detection is important step. If disease is not detected at early
stage will lead to farmer’s economical loss. The system will take input as images of citrus
plant and gives output as detected diseases through CNN and classication algorithms.
So system is proposed to classify the diseases and recommend the pesticides.

3.2 Scope of Project

• The proposed system is able to detect the dierent citrus plant diseases such as
Black spot, canker, scab, greening, and Melanose.

• Citrus plant disease classication has practical applications in the eld of plant
disease recognition based on their visual symptoms.

• The system will be able to detect diseases which are at early stage of the disease
and recommend the fertilizers according to the disease.

• The proposed method contains ve stages such as preproccessing, segmentation,

feature extraction, reduction, fusion, and classication.

15
3.3. PROJECT OBJECTIVES CHAPTER 3. PROPOSED WORK

3.3 Project Objectives

• To develop system to detect plant disease.

• To recommend insecticides as well as pesticides for respective plant disease.

• To create database of suggestive pesticides for respective diseases.

3.4 Project Constraints

The system has some limitations which are :-

• It detects only disease but it is unable to give the exact damage i.e. how much plant
is infected with the disease.

• System is unable to show the position of the damage.

• We only used one deep learning-based CNN model in this system other deep learning
models can be also used.

Citrus Plant Disease Classifcation and 16 VPKBIET, Baramati

Recommendation System Using Deep Learning
Chapter 4

Project Requirement Specication

4.1 Performance Requirements

For the best performance of the software user must follow the sequence of the activities
to achieve the required results. Do not proceed to recognise text before the picture is
captured. While using the software, users action must be consistent and unique. input
to the software must be in proper format.

4.2 Software Quality Attributes/Requirements

Some of the quality of attributes identied include.

• Portability : In API portability can be dened as compatibility of application with

platform upgraded or downloaded versions.

• Flexibility : The architecture of the application will be exible enough for some
later requirements change or application enhancement.

• Maintainability : Whenever there is a change in requirement or bug found the

application will be easily maintainable.

17
4.3. SECURITY REQUIREMENTS CHAPTER 4. PROJECT REQUIREMENT SPECIFICATION

4.3 Security Requirements

Security requirements are needed to prevent any malicious attack that can take place
on the project. These requirements are as follows:-

• The information need be secured from ethical hackers.

• The type of data is produced at the website should not be exposed to fertilizers
company, so that they could not manipulate the market.

4.4 Hardware Requirements

• System Processor : Core i5 processor 10th generation 8 GB RAM

• SSD : Minimum 512 GB

• RAM : Minimum 8 GB

4.5 Software Requirements

• Operating system : Windows 11 (Intel/AMD 64-bit)

• Coding Language : Python (version 3.7.0)

• Libraries : Keras, Tensorow, Matplotlib, Seaborn, Numpy, Pandas , Tkinter

• IDE : Jupyter Notebook, Anaconda, VSCode

Citrus Plant Disease Classifcation and 18 VPKBIET, Baramati

Recommendation System Using Deep Learning
Chapter 5

Systems Architecture

Fig. Systems Architecture Diagram

19
 CHAPTER 5. SYSTEMS ARCHITECTURE

Firstly system will take input images of the citrus plant which healthy as well as af-
fected by the diseases. After that it will be given to the next step and data is downloaded
from the keras. After that data is splitted into training data, testing data and validated
data is preprocessed i.e. resized and rescaled. Also data is augmented. Input layers are
dened and hidden also dened. As output needed for data is data classied into ve
dierent classes.
So, ve neurons are passed at the output layer. Here, CNN is used which contains
ve convolutional with simultaneous max-pooling layers. Model is build with the data
as well as performance also evaluated. Dierent images were tested with random data
of citrus plant and output is checked. Lastly based on disease fertilizer is recommended
with the help of fertilizer dataset.

Citrus Plant Disease Classifcation and 20 VPKBIET, Baramati

Recommendation System Using Deep Learning
Chapter 6

Project Planning

6.1 Project Estimates

Software Engineering Estimation models: Cost estimation simply means a tech-

nique that is used to nd out the cost estimates. The cost estimate is the nancial spend
that is done on the eorts to develop and test software in Software Engineering

21
6.1. PROJECT ESTIMATES CHAPTER 6. PROJECT PLANNING

1. COCOMO :– The Constructive Cost Model(COCOMO) is an algorithmic soft-

ware cost estimation model developed by Barray W. Boehm. The Model uses a basic
regression formula with parameters that are derived from historical project data and
current project characteristics.
COCOMO consists of a hierarchy of three incresingly detailed and accurate forms. The
rst level, Basic COCOMO is good for quick, early,rough order of magnitude estimates
of software costs, but its accuracy is limited due to its lack of factors to account for
dierence in project attributes (Cost Drivers). Intermediate COCOMO takes these Cost
Drivers into account and detailed COCOMO additionally accounts fr the inuence of
individual project phase.
Basic COCOMO Model Formulae :
1. Eort Applied (E) = ab * (KLOC)(bb ) -[man-months]
2. DevelopmentTime(D) =cb * (Ef f ortApplied)db - [months]
3. PeopleRequired(P) = (EortApplied)/(DevelopmentTime)[count]
Calculations for Project :

Citrus Plant Disease Classifcation and 22 VPKBIET, Baramati

Recommendation System Using Deep Learning
6.1. PROJECT ESTIMATES CHAPTER 6. PROJECT PLANNING

Budget Estimation:
Estimation is the process of nding an estimate, or approximation, which is a value that
can be used for some purpose even if input data may be incomplete, uncertain, unstable.
Estimation determines how much money, eort, resources, and time it will take to build
a specic system or product Cost of Project:
Equation for calculation of cost of project using COCOMO model is:
C = D * Cp
Where,
C = Cost of project
D = Duration in month
Cp= Cost incurred per person-month,
Cp=Rs.3000/- (per person-month) (approx.)
C = 9 * 3000
= 27000/- Hence according COCOMO model the cost of project is 27000/-(approx)

Citrus Plant Disease Classifcation and 23 VPKBIET, Baramati

Recommendation System Using Deep Learning
6.2. TEAM STRUCTURE CHAPTER 6. PROJECT PLANNING

6.2 Team Structure

Citrus Plant Disease Classifcation and 24 VPKBIET, Baramati

Recommendation System Using Deep Learning
Chapter 7

Project Schedule

7.1 Project Breakdown Structure

Fig. 7.1 Project Break down structure

25
7.2. TASK NETWORK CHAPTER 7. PROJECT SCHEDULE

7.2 Task Network

Fig. 7.2 Task Network

Citrus Plant Disease Classifcation and 26 VPKBIET, Baramati

Recommendation System Using Deep Learning
7.3. TIME-LINE CHARTS CHAPTER 7. PROJECT SCHEDULE

7.3 Time-line charts

Fig. 7.3 Time-line charts

Citrus Plant Disease Classifcation and 27 VPKBIET, Baramati

Recommendation System Using Deep Learning
Chapter 8

Project Design

8.1 DataFlow Levels

8.1.1 Dataow Level 0

28
8.1. DATAFLOW LEVELS CHAPTER 8. PROJECT DESIGN

8.1.2 Dataow Level 1

Citrus Plant Disease Classifcation and 29 VPKBIET, Baramati

Recommendation System Using Deep Learning
8.1. DATAFLOW LEVELS CHAPTER 8. PROJECT DESIGN

8.1.3 Dataow Level 2

Citrus Plant Disease Classifcation and 30 VPKBIET, Baramati

Recommendation System Using Deep Learning
8.2. UML DIAGRAMS CHAPTER 8. PROJECT DESIGN

8.2 UML Diagrams

8.3 Usecase Diagram

Citrus Plant Disease Classifcation and 31 VPKBIET, Baramati

Recommendation System Using Deep Learning
8.4. ACTIVITY DIAGRAM CHAPTER 8. PROJECT DESIGN

8.4 Activity Diagram

Citrus Plant Disease Classifcation and 32 VPKBIET, Baramati

Recommendation System Using Deep Learning
8.5. CLASS DIAGRAM CHAPTER 8. PROJECT DESIGN

8.5 Class Diagram

Citrus Plant Disease Classifcation and 33 VPKBIET, Baramati

Recommendation System Using Deep Learning
Chapter 9

System Algorithms and

Implementation

9.1 Dataset Descriptions

Dataset Description:This Dataset taken from our base research paper.We used dataset of
leaves in our project,which contains 1036 images spread across 5 classes.This dataset con-
tains various types of disease such as canker,black spot,mealnose,healthy,greening.The
rst le contains 171 images of black spot,the second le contains 163 images of canker,the
third contains 204 images of greening,the four contains 485 images of healthy,the last
one contains 13 images of melanose.The Leaves datsets contains images that facilitates
training ,testing and validation during utilization of deep learning algorithun for plant
disease classication or recommendations.

Sr.No Name No of Images

1 Black Spot 171
2 Canker 163
.
3 Greening 204
4 Healthy 485
5 Melanose 13

34
9.2. CNN ALGORITHM CHAPTER 9. SYSTEM ALGORITHMS AND IMPLEMENTATION

9.2 CNN Algorithm

9.2.1 Algorithm Steps

Step 1 :

Firstly,images of the citrus leaves dataset will be downloaded from keras.

Step 2 :

Image Input. - The input layer includes the Convolution layer, ReLu activation layer,
and layer(max) pooling.

Step 3 :

Convert the images into an array.

Step 4 :

Set a value for each feature with dimensions.

Step 5 :

Read the image from the training directory and applied image pre-processing techniques-
data cleaning, data transformation, and dimensionality reduction.

Step 6 :

Feature extraction using CNN.

Step 7 :

Classify images into healthy and disease classes.

Citrus Plant Disease Classifcation and 35 VPKBIET, Baramati

Recommendation System Using Deep Learning
9.3. CODE CHAPTER 9. SYSTEM ALGORITHMS AND IMPLEMENTATION

9.3 Code

Citrus Plant Disease Classifcation and 36 VPKBIET, Baramati

Recommendation System Using Deep Learning
9.3. CODE CHAPTER 9. SYSTEM ALGORITHMS AND IMPLEMENTATION

Citrus Plant Disease Classifcation and 37 VPKBIET, Baramati

Recommendation System Using Deep Learning
9.3. CODE CHAPTER 9. SYSTEM ALGORITHMS AND IMPLEMENTATION

Citrus Plant Disease Classifcation and 39 VPKBIET, Baramati

Recommendation System Using Deep Learning
 CHAPTER 10. TEST CASES

Chapter 10

Test Cases

Citrus Plant Disease Classifcation and 41 VPKBIET, Baramati

Recommendation System Using Deep Learning
Chapter 11

Experimental Results

11.1 GUI

11.1.1 Load Image Module

Screenshot 1: Input

This screenshot shows the graphical user interface (GUI) of the Load Image module.
The user is presented with a button labeled ”Upload Image” that allows them to select
an image le from their device. The user can click this button to open a le dialog and
choose the desired image.

42
11.1. GUI CHAPTER 11. EXPERIMENTAL RESULTS

11.1.2 Process Module

Screenshot 2: Process

In this screenshot, we can see the GUI of the Process module. The uploaded image is
displayed in a designated area. Below the image, there is a button labeled ”Predict”
that triggers the classication of disease. Clicking this button initiates the algorithm to
process the image and classify the disease and recommend fertilizer.

Citrus Plant Disease Classifcation and 43 VPKBIET, Baramati

Recommendation System Using Deep Learning
11.1. GUI CHAPTER 11. EXPERIMENTAL RESULTS

11.1.3 Output Module

Screenshot 3: Output

The Output module screenshot showcases the result of the disease classication process.
A text box is provided where the disease name is displayed. The user can see the disease
name in this area. Additionally, system recommended the fertilizer according to the
disease.

Citrus Plant Disease Classifcation and 44 VPKBIET, Baramati

Recommendation System Using Deep Learning
11.2. WORKING MODULES CHAPTER 11. EXPERIMENTAL RESULTS

11.2 Working Modules

11.2.1 Disease Detection

There are some diseases that are the most dangerous, such as black spot,canker,scab,greening
and melanose classes.It takes selects several common citrus diseases as experimental ob-
jects Disease problems certainty aect crops throughout their growing cycle in agriculture
eld,disease detection is important step.If disease is not detected at early stage will lead
to farmer’s economical loss.Machine vision framework uses image processing techniques
to perform such specic work,that is why image processing assumes an exceptionally
signicant job in their capabilities.

11.2.2 Recommendation based on diseases

The rst model predicts the disease due to which plant is infected and then by display-
ing not only disease name but also gives the recommendation that how to degrade this
disease and which fertilizers,insecticides and pesticides that used to overcome this prob-
lem.It recommend the user that what they should be done.

Citrus Plant Disease Classifcation and 45 VPKBIET, Baramati

Recommendation System Using Deep Learning
11.3. EXPERIMENTAL RESULTS AND DISCUSSIONS
CHAPTER 11. EXPERIMENTAL RESULTS

11.3 Experimental Results and Discussions

11.3.1 Confusion Matrix

11.3.2 Precision, Recall and F1 Score

Citrus Plant Disease Classifcation and 46 VPKBIET, Baramati

Recommendation System Using Deep Learning
11.3. EXPERIMENTAL RESULTS AND DISCUSSIONS
CHAPTER 11. EXPERIMENTAL RESULTS

11.3.3 Accuracy

11.3.4 Loss

Citrus Plant Disease Classifcation and 47 VPKBIET, Baramati

Recommendation System Using Deep Learning
Chapter 12

Conclusion and Future Scope

12.1 Conclusion

The proposed CNN-based leaf disease identication model is capable of dierentiating

between diseased and healthy citrus leaves. In this system, the dataset of 1036 images
is processed. The proposed system is used to tackle the problem of classifying diseases
of citrus leaf images. In this system total of 6 convolutional layers are used, which helps
to yield disease classication of citrus leaves into black spot, canker, scab, greening, and
melanose classes. After that based on disease, it recommends fertilizers. The accuracy
of this model is 97.9 %. The pre-trained model of VGG16 is used on same dataset. For
the same dataset VGG16 model gives an accuracy of 84.3 %. From this, we conclude
that our CNN model gives better accuracy as compared to VGG16 model.

48
12.2. FUTURE SCOPE CHAPTER 12. CONCLUSION AND FUTURE SCOPE

12.2 Future Scope

The currently proposed system not only helps to identify the disease but also provide
recommendation on that disease but it is only useful for the leaves of the citrus plant
family.
We can do some developments in this system such as system will be identied the disease
of whole citrus plant parts and also identifying the spot where the plant is infected by
the disease and also showing the percentage value that the disease is spread on plant
parts. In the future scope, we can make android which will allow farmers to click picture
of citrus leave and upload it on app and they will get infection to specic leave and exact
percentage of damage to leaves.

Citrus Plant Disease Classifcation and 49 VPKBIET, Baramati

Recommendation System Using Deep Learning
References

[1] Asad Khattak,Muhamad Usma Asghar,Ulfat Batool,Muhammad Zubair As-

ghar,Hayat Ullah,Mabrook Al-Rakhami,And Abdu Gumaei,”Automatic Detection
of Citrus Fruit and Leaves Diseases Using Deep Neural Network Model”,Received
May 29, 2021, accepted July 2, 2021, date of publication July 13, 2021, date of
current version August 18, 2021.

[2] Wnyane Pan,Jiaohua Qin,Xuyu Xiang,Yan Wu1,Yun Tan,And Lingyun Xiang,”A

Smart Mobile Diagnosis System for Citrus Diseases Based on Densely Connected
Convolutional Networks”,date of publication June 26, 2019, date of current version
July 18, 2019. Digital Object Identier 10.1109/ACCESS.2019.2924973

[3] Muhammad Zia Ur Rehman,Fawad Ahmed,Muhammad Attique Khan,Usman

Tariq,Sajjad Shaukat Jamal,Jawad Ahmad,Iqtadar Hussain,”Classication of Cit-
rus Plant Diseases Using Deep Transfer Learning”,Computers,Materials Continua
Tech Science Press DOI:10.32604/cmc.2022.0190

[4] Muhammad Hassam,Muhammad Attique Khan,Ammar Armghan,Sara A Althu-

biti,Majed Alhaisoni,Abdullah Alqahtani,Seifedine Kadry,Yongsung Kim,”A Single
Stream Modied MobileNet V2 and Whale controlled Entropy based Optimiza-
tion Framework for Citrus Fruit Diseases Recognition”,IEEE Access, 2022, doi:
10.1109/ACCESS.2022.3201338

[5] Vinay Kukreja,Poonam Dhiman,”A Deep Neural Network based disease detection
scheme for Citrus fruits ”,IEEE Xplore Part Number: CFP20V90-ART; ISBN: 978-
1-7281-5461-9

50
Appendix A

Appendix

51
Appendix B

Base Paper

1] Asad Khattak,Muhammad Usama Asghar,Ulfat Batool,Muhammad Zubair Asghar,Hayat

Ullah,Mabrook Al-Rakhami,And Abdu Gumaei,”Automatic Detection of Citrus Fruit
and Leaves Diseases Using Deep Neural Network Model”,Received May 29, 2021, ac-
cepted July 2, 2021, date of publication July 13, 2021, date of current version August
18, 2021.

52
Appendix C

Tools Used

Overleaf : Use of Overleaf is free and open source. With a sign-up procedure, you may
create, edit, and share your projects. Overleaf is a real-time editor used for projects and
research papers. It is a LaTeX editor using the cloud to write, edit, and publish scientic
documents. Multiple users may access Overleaf at once.
Anaconda Navigator: Anaconda is an open-source tool. Anaconda Navigator also
includes a graphical user interface. It can be used for Python and R programming
languages for data science that seeks to make deployment and package management
simpler. Anaconda Navigator can launch any applications and manage the Anaconda
package without using the command line interface.
Jupiter Notebook: Jupiter Notebook is a web-based application for creating and shar-
ing any documents. Jupiter notebook is mostly used in Python programming language-
related projects. Jupiter Notebook can support programming languages such as R and
Python.
Diagrams.Net: Free online diagram software is available at Diagrams.Net..It can be
used for making owcharts, process diagrams, DFD diagrams, UML diagrams,s and net-
work diagrams.

53