First Phase PROJECT REPORT

On

“Leaf diseases detection by using machine learning”

Submitted in partial fulfillment of the requirements to

Malla Reddy University

For the award of the degree
BACHELOR of TECHNOLOGY

In

COMPUTER SCIENCE &ENGINEERING

Submitted by

2011CS010308 V.Jaswanth

2011CS010271 P.Bhaskar

2011CS010348 K.Hardeep

2011CS010282 Smd.Fazil

Under the guidance of

Mr. K. Siva Krishna, M. Tech, Ph.D

Assistant Professor in School Of Engineering, Dept. of CSE

DEPARTMENT OF COMPUTER SCIENCE & ENGINEERING

Malla Reddy University

(As per Telangana State Private Universities Act No.13 of 2020 and 
G.O.Ms.No.14, Higher Education (UE) Department)
 DEPARTMENT OF COMPUTER SCIENCE & ENGINEERING
Malla Reddy University
(As per Telangana State Private Universities Act No.13 of 2020 and 
G.O.Ms.No.14, Higher Education (UE) Department)

CERTIFICATE

This is to certify that the Project Work titled, “Leaf diseases detection by using machine
learning” Is a bonafide work of V.Jaswanth (2011CS010308),
P.Bhaskar(2011CS010271), K.Hardeep Mehar (2011CS010348), Shaik Mohammad
Fazil(2011CS010282) who carried out the work under my supervision and submitted in
partial fulfillment of the requirements for the award of the degree of BACHELOR OF
TECHNOLOGY in COMPUTER SCIENCE and ENGINEERING by Malla Reddy
University during the academic year 2021-2022.

Guide Name: Signature of Guide:

 DECLARATION

We hereby inform that this main project entitled “Canteen Automation System”

has been carried out and submitted in partial fulfilment for the award to the Degree of

Bachelor of Technology in Computer Science and Engineering to Malla Reddy

University, Hyderabad under the guidance of Mr. K. V. Siva Krishna, MTech, Assistant

Professor, Department of Computer Science and Engineering. The work embodied in this

project work is original and has not been submitted in part or full for any degree of this or

any degree of any other university.

By

V.Jaswanth (2011CS010308)

P.Bhaskar (2011CS010271)

K.Hardeep Mehar (2011CS010348)

Shaik Mohammad Fazil (2011CS010282)

ABSTRACT

Now a day’s plant diseases discovery has received increasing attention in looking at greatly sized field
of the years produce. In this project we need of simple plant Leaf’s disease discovery system that would
help moves-forward in farming. Early information on the years produce being healthy and disease
discovery can help the control of diseases by detecting them. Leaf diseases are the major problem in
agricultural sector, which affects crop production as well as economic profit. Early detection of diseases
using deep learning could avoid such a disaster. It is observed that the development in agriculture is
sluggish nowadays due to the attack of diseases. Many farmers detect diseases by their previous
experience or some take help from experts. Traditional ways are often used to detect the diseases by the
farmers. So, there is the possibility of an inaccurate diagnosis of diseases having very large similarity in
their symptoms. So, it is essential to move towards the new strategies for automatic diagnosis and
controlling of disease. So, there is a need for an automatic, accurate and less expensive machine vision
system for detection of disease from leaf images.

In addition, crop diseases contribute directly and indirectly to the spread of human infectious diseases
and environmental damage. As these diseases are spreading worldwide causing damage to the normal
functioning of the plant and also damaging the financial condition by significantly reducing the quantity
of crops grown. The crop production losses its quality due to much type diseases and sometimes they
occur but are even not visible with naked eyes. We need different types of digital image processing
techniques to detect the plant diseases. To detect these plant diseases many fast techniques, need to be
adopt. In this project, we use SVM to detect these diseases.

Keywords: Financial condition, Crop Diseases, Digital Image Processing, Support Vector Machine
 INDEX
CONTENTS PAGE NO

1. INTRODUCTION 6-8

1.1 Introduction of the Project 6

1.2 Existing System 7

1.3 Problems of the Existing Systems 7

1.4 Proposed System 7-8

1.5 Benefits of the Proposed System 8

1.6 Literature Survey and Review 8

2. ANALYSIS 8-22

2.1 Requirements Analysis 9-13

2.1.1 Functional Requirements Analysis 9-11

2.1.2 User Requirements 12

2.1.3 Non Functional Requirements 12-13

2.1.4 System Requirements 13

2.2 Modules Description 14

2.3 Feasibility Study 14-17

2.3.1 Technical Feasibility 15

2.3.2 Operational Feasibility 16

2.3.3 Behavioral Feasibility 16

2.3.4 Economical Feasibility 17

2.4 Process Model used 17-20

2.5 Hardware and Software Requirements 21

3.0 REFERENCES 22
1. INTRODUCTION
1.1 INTRODUCTION:
Plant diseases can affect the whole produce which makes early diagnosis and classification vital. This
helps save resources, time, and money and adopt timely preventive measures to avoid the affliction in
the future. To detect affected areas on plant leaves, there are two major approaches that can be followed.
The first approach is Image Processing by applying various techniques: filtering, clustering, histogram
analysis among many others, to find the region of interest. The region of interest can effectively
constitute the damaged portion of the leaf and the shape and size analysis can detect the disease that is
afflicting the plant. Image processing algorithms are easy to understand and the use of Python libraries,
such as OpenCV, make applications of these techniques simpler. However, in these algorithms, the
average accuracy of disease detection is not very high.

For better agricultural productivity health of plant is a primary concern. Diseases hinder the normal state
of a plant and potentially modify or interrupt its vital mechanisms such as fertilization, photosynthesis,
transpiration, germination etc. Time and again plants get various diseases depending upon the factors
like environment, season, soil, bacteria and others. The conventional process of plants disease detection
with bare eyes observation method is tiresome and is non-effective. So identifying the plant disease for
farmers requires help of related filed specialist most of the time. Hiring the related filed experts may cost
farmers heavily and use of pesticides without knowledge will degrade the quality land and harm the
living organisms. So utilizing available technology to identify the plant diseases may be a viable
solution. Plant disease recognition by visual method is cumbersome task, less accurate and can be
applied only in limited areas.

Depending upon the texture (shape, size, roughness, intensity, etc.) plant diseases can be predicted in
some cases and in others it may require further test. This research is focused on classifying and
recognizing images based on the plant leaf textures such as contrast, correlation, entropy, inverse
difference moments and leaf colors (red, green and blue). There are sixteen different plant leaf
categories considered as healthy or other predefined disease for this work.

The SVM algorithms in order to pick out the efficient and accuracy. SVM is a supervised learning
algorithm and it works well on classification issues. To evaluate the performance of a system, cross-
validation is a common method to deal with small training sets in desktop learning is typically used .
Photo Courtesy (pc) is used to grading of plant diseases. In the texture leaf records are computed for the
beneficial segments, and then the extracted facts are surpassed through the SVM classifier
1.2 Existing System
Many farmers detect diseases by their previous experience or some take help from experts. Traditional
ways are often used to detect the diseases by the farmers. So, there is the possibility of an inaccurate
diagnosis of diseases having very large similarity in their symptoms. So, it is essential to move towards
the new strategies for automatic diagnosis and controlling of disease.

Even if the farmers hire the expert the farmer has to pay the high fairs for the inspection and the

1.3 Problems of the Existing Systems

========================================
1.4 Proposed System

The first part of the proposed plant disease detection system is the process of training. At this stage, the
images of the plants are obtained using a digital camera. Then the image pre -processing techniques are
applied to these images. After pre-processing, useful image features are extracted using feature
extraction technique that will be used as training samples for the support vector machine algorithm (the
proposed machine learning algorithm in this system). In the detection phase, the images will be
obtained first by capturing them with a digital camera. After that, the image processing techniques
referred to in the training phase will be applied and finally, the case will be classified as either infected
or healthy through support vector machine (SVM).

1.5 Benefits of proposed system

The main purpose of proposed system is to detect the diseases of plant leaves by using feature
extraction methods where features such as shape, color and texture are taken into consideration. Support
vector machine (SVM), a machine learning technique is used in classifying the plant leaves into healthy
or diseased and if it is a diseased plant leaf, SVM will give the name of that particular disease.
Suggesting remedies for particular disease is made which will help in growing healthy plants and
improve the productivity.
 First the images of various leaves are acquired using high resolution camera so as to get the better
results & efficiency. Then image processing techniques are applied to these images to extract useful
features which will be required for further analysis. The basic steps of the system are summarized as:

Fig.1 Proposed System

 Use of estimators for automatic Initialization of cluster centers so there is no need of user input at the
time of segmentation.

 The detection accuracy is enhanced with proposed algorithm.

 Proposed method is fully automatic while existing methods require user input to select the best
segmentation of input image.

 It also provides environment friendly recovery measures of the identified disease.

1.6 Literature Survey and Review

Some papers are describing to detection leaf disease using various methods suggesting the
various implementation ways as follow. Visual Analysis, Image Processing and Optical Sensor are
mainly implemented in three ways as the disease detection method. By using these three methods, the
system can be developed to detect the disease earlier and that can overcome the challenges and
disadvantages. By means of the methods comparison, disease detection by using visual analysis does not
give the accurate output while in case of optical sensor, the system is not easy to implement and costly.
So, image processing is the only way to build the simple, robust and accurate disease detection system .
While working with image processing, on the other hands, the database collection is the most
challenging task. For database collection, it is necessary to collect the basic information about the crop
and its diseases as the important task. Therefore, a detail study should be done on the types of disease,
their symptoms on crop and the patterns of disease. By observing the patterns of disease, the system will
get designed.

The mainly occurring diseases on leaf are Bacterial disease, Fungal disease, Viral disease and
diseases due to insects. The paper gives the detailing of these diseasesIn a system to distinguish diseases
of plants utilizing image processing. This goes under automatic plant disease identification. There are
number of colors for disease set apart as a dark spot and intensity for color segmentation. RGB image
can be utilized for color segmentation. In this paper an examination of the result of CIELAB, HSI and
YCbCr color space during the time spent disease spot identification is finished. Image smoothing is
finished by middle channel. Otsu technique on color component to distinguish the disease spot can be
connected for limit values. An algorithm which is autonomous of background plant sort, noise and
disease spot color was produced and examinations were passed out on various "Monocot" and "Dicot"
family plant leaves with both, noise free (white) and noisy background.

2. ANALYSIS
2.1 Requirements Analysis
2.1.1 Functional Requirements Analysis
-----------------------------
2.1.2 User Requirements

-----------------------------------------------------.

2.1.3 Non-functional requirements

1. Security

 System needs to control the user access and session

 It needs to store the data in a secure location and stored in a secure format

 It requires a secure communication channel for the data.

2. Concurrency and Capacity

System should be able to handle multiple computations executing simultaneously, and potentially
interacting with each other.

3. Performance

Performance is generally perceived as a time expectation. This is one of the most important
considerations especially when the project is in the architecture phase.

4. Reliability

It is necessary to ensure and notify about the system transactions and processing as simple as keep a
system log will increase the time and effort to get it done from the very beginning. Data should be
transferred in a reliable way and using trustful protocols.

5. Maintainability

Well-done system is meant to be up and running for long time. Therefore, it will regularly need
preventive and corrective maintenance. Maintenance might signify scalability to grow and improve the
system features and functionalities.

6. Usability

End user satisfaction and acceptance is one of the key pillars that support a project success. Considering
the user experience requirements from the project.

2.1.4 System requirements:

------------------------------------
2.2 Modules Description
======================================================

2.3 Feasibility Study

========================
2.3.1 Technical Feasibility
2.3.2 Operational Feasibility:
==============================

2.3.3 Behavioral Feasibility

2.3.4 Economic Feasibility:

2.4 Process Model used
================

2.4.3 Control Flow Diagram

==============================
2.5 SOFTWARE & HARDWARE REQUIREMENTS
Hardware Requirements

Processor: 2.5 gigahertz (GHz) frequency or above.

 RAM: A minimum of 4 GB of RAM.

 Hard disk: A minimum of 20 GB of available space.

 Input Device: High resolution camera

 Monitor: Minimum Resolution 1024 X 768.

Software Requirements

 Operating System: Windows 7 and above.

 Programming language: Python

 Platform: Jet Brains PyCharm Community Edition 2018.3.5 x64

3.0 REFERENCES

[1] Ko Ko Zaw, Zin Ma Ma Myo, and Wah Wah Hlaing. 2018. “Multiclass Support Vector Machine Based
Detection and Classification of Leaf Diseases”, 11th National Conference on Science and Engineering,
YTU, Yangon, Myanmar

[2] A. Miyatra, S. Solanki. 2014. “Disease and Nutrient Deficiency Detection in Cotton Plant,”
International Journal of Engineering Development and Research, vol. 2, no 2, pp. 2801-2804.

[3] V. A. Gulhane, A. A. Gurjar. 2011. “Detection of disease on cotton Leaves and Its Possible Diagnosis”,
International Journal of Image Processing (IJIP), vol. 5 : no 5 : pp. 590-598.

[4] S. S. Panchal, R. Sonar. 2016. “Pomegranate Leaf Disease Detection Using Support Vector Machine,”
International Journal of Engineering and Computer Science, vol. 5, no 6, pp. 16815-16818.

[5] V. M. Tiwari, T. Gupta. 2017. “Plant Leaf Disease Analysis using Image Processing Technique with
Modified SVM-CS Classifier,” International Journal of Engineering and Management Technology, vol. 5,
no. 1, pp. 11-17.

[6] A. N. Rathod , B. A. Tanawala, V. H. Shah. 2014. “Leaf disease detection using image processing and
neural network”, IJAERD vol. 1, no. 6, June, pp. 1-10.

[7] S. Jayaraman, S. Esakkirajan , and T. Veerakumar. 2009. Digital Image Processing. U.S.A.: McGraw Hill
Co.

[8]Foody, M. G., and Mathur, A. 2004b. Toward Intelligent Training of Supervised Image Classifications:
Directing Training Data Acquisition for SVM Classification. Remote Sensing of Environment, 93, 107 -
117.