“COTTON LEAF DISEASE IDENTIFICATION USING

PATTERN RECOGNITION TECHNIQUE BASED ON IOT”

Submitted by

NAYAN LINGAYAT

ROHINI TAYADE

MANSI MAHAJAN

Under the guidance of

MS.SONAL PATIL

Department of Information Technology & Engineering

G.H.RAISONI INSTITUTE OF ENGINEERING & MANAGEMENT ,

JALGAON (M.S.)
KAVAYITRI BAHINABAI CHAUDHARI NORTH MAHARASHTRA
UNIVERSITY, JALGAON

Year-2019 -2020

I
G.H.RAISONI INSTITUTE OF ENGINEERING AND MANAGEMENT,

JALGAON.

Department of Information Technology & Engineering

CERTIFICATE

This is to certify that the Minor Project (Stage-I) entitled “cotton leaf disease
identification using pattern recognition technique based on IOT” has been
carried out by Nayan Lingayat, Rohini Tayde, Mansi Mahajan under my
guidance in partial fulfillment of the degree of Bachelor of Engineering in
Information Technology & Engineering of Kavayitri Bahinabai Chaudhari
North Maharashtra University, Jalgaon during the academic year 2019-2020.
To the best of my knowledge and belief this work has not been submitted
elsewhere for the award of any other degree.
(prof.Sonal patil) Dr.A.G.Mathew Ms.Sonal Patil

Guide Principle HOD

II
 ACKNOWLEDGEMENT

we would like to express my special thanks of gratitude to my project guide as

well as our head of department Ms. Sonal patil who gave us the golden
opportunity to do this wonderful project on the topic” cotton leaf disease
identification using pattern recognition technique based on Iot” , which also
helped me in doing a lot of research and we come to know about so many new
things.

We are thankful to sonal maam for the wonderful suggestion throughout the
project completion and being concern to us.

We are sincerely thankful to all the faculty members of CSE-IT department

who help and motivate us most of the time.

NAYAN LINGAYAT

ROHINI TAYDE

MANSI MAHAJAN

III
 CONTENTS
Topic Page No

Abstract 1

1. Introduction 2

1.1 Background 2

1.2 Motivation 2

1.3 Problem Definition 2

1.4 Scope 3

1.5 Objective 3

1.6 Selection of Life cycle Model for Development 4

1.7 Organization of Report 4

1.8 Summary 5

2. Project Planning and Management 6

2.1 Feasibility Study 6

2.2 Risk Analysis 7

2.3 Project Scheduling 7

2.4 Cost Estimation 7

IV
3. Analysis 8

3.1 Functional and non-Functional Requirements 8

3.2 H/w and S/w Requirement 9

3.3 software Requirement’s Specifications 9

4. Design 10

4.1 System Architecture 10

4.2 Data flow Diagram. 12

4.3 UML Diagrams 13

5. Conclusions and Future work 14

Bibliography 16

V
 TABLE INDEX
Table Page No.

1 Cost Estimation 7

VI
 FIGURE INDEX
Figure Page No.

1 system Architecture 10
2 Data Flow Diagram 12
3 UML diagram 13

VII
 ABSTRACT

The large number of individuals depends on cotton crop. the popularity of

cotton disease are of the most important as they have a cogent and
momentous impact on quality and production of cotton. Cotton disease
identification is an art and science. Now a day’s image processing technique
becoming a key technique for diagnosing the many features of the crop. This
paper mainly focuses detection of varied cotton crop diseases and to classify
them.

There are classification techniques like k-Nearest classifier , k-means

Clustering. A sensible phone empowers farmer to stay updated with the going
conditions of his agricultural land using IOT at any time and any part of the
planet. IOT technology can reduce the value and enhance the productivity of
traditional farming, not every farmer buy smart phone they mainly focuses on
the crops growing, there is a lagging thing in most of the farmers.

1
 CHAPTER-1

INTRODUCTION

1.1 Background

India is agriculture country where in more than 65% population depends on

agriculture. Cotton is very important crop in our country and if some disease are
affected on that the economical condition of the farmer gets collapsed. Hence the
detection of those diseases are very important. The various cotton leaf diseases are
Red spot disease (Lalya),white spot disease (Pandhari Mashi), Crumple leaf disease
(Kokada).

But somehow the farmers did not get the exact name or solutions for various
diseases, that is why they get heavy load of loss in the market. Best in this we get the
solution before very late.

1.2 Motivation

India is the huge market for the textile industry, which is fastest growing market. But
the raw material for this, is cotton which is the main supplement for the fulfillment
of textile industries which are they trying to get in very cheap price.

But farmers take lot of efforts to get the best cotton, very few of them get the
best crops because they take precautions to their crops to not any disease get fall on
them. But it is very costly for them and at last they did not get that much profit to
fulfill their need, For this we have to find solution.

1.3 problem definition

Normally if disease is get detected by the farmer he contacts to the Experienced

2
person of that area and get solution for the same but if the detection and
identification of disease not correct then it badly affect on the cotton plant. In second
case farmer contacts to the owner of pesticide shop who suggests some treatment
with respect to his experience. Third case is that farmers are just going with nature
they think that the diseases will get cleared automatically in some period of span.

1.4 Scope

All the farmers who are in trouble in such problem like they are facing so much loss
in the cotton crops and they willing to get the solution as soon as possible, our
proposed system is definitely going to reduce their stress. In that case lots of farmers
get the advantage of this system. They can easily find the solution in less time.

1.5 Objective

The main purpose of this is to identify the type of disease and quantify the damage of
cotton crop thereby providing the treatment for the respective disease. We are going
to do this identification and detection of disease by using image processing
techniques on the cotton leaf.

After the detection of possible disease on cotton leaf as well as possible

treatment, precautions, pesticides suggestion, remedies should be provide to the
farmer. Farmer himself can provide cotton leaf to our system and get the details
about cotton leaf diseases and treatment. Various other promising feature can be
added in feature extraction process for making the system more robust. This may
help in increasing the performance of the system. As the identification of the
problem is not only important part of this research but if we are going to provide
solution to the cotton disease will help for all farmer.

3
1.6 Selection of life cycle for development

Waterfall model

The Waterfall Model was first Process Model to be introduced. It is also referred to
as a linear-sequential life cycle model. It is very simple to understand and use. In a
waterfall model, each phase must be completed fully before the next phase can
begin. This type of model is basically used for the for the project which is small and
there are no uncertain requirements. At the end of each phase, a review takes place to
determine if the project is on the right path and whether or not to continue or discard
the project. In this model the testing starts only after the development is complete. In
waterfall model phases do not overlap.

1.7 Organization of report

The information presented at the report is divided in to 5 chapters, after this

introductory chapter, chapter 2 describes the project planning and management in
this it summarize the important part of project like cost estimation , feasibility study

4
scheduling of the project, in detail.

Chapter 3, summarize the analysis of the project that the hardware and software

requirements specifications.

Chapter 4, describe the system architecture and data flow diagram of the project.

1.8 summary

The crop losses due to diseases are approximately 10 to 30%. Farmers judge the
diseases by their experience but this is not accurate and proper way. Sometimes
farmers call the experts for detecting the diseases but this also time consuming way.
The diseases mostly on leaves and on stem of plant.

The diseases are viral, bacterial, fungal, diseases due to insects, rust,
nematodes etc. on plant. It is important task for farmers to find out these diseases as
early as possible. Most leaf diseases are caused by fungi, bacteria and viruses. Fungi
are identified primarily from their morphology, with emphasis placed on their
reproductive structures. Bacteria are considered more primitive than fungi and
generally have simpler life cycles.

5
 Chapter 2

PROJECT PLANNING AND MANAGEMENT

2.1 Feasibility study

The feasibility of the system can be examined under Technical feasibility,

Economical feasibility & Operational feasibility.

2.1.1 Technical Feasibility

Technical feasibility is one of the first studies that must be conducted after the
project has been identified. In large engineering projects, consulting agencies that
have large staff of engineers and technicians conduct technical studies dealing with
the projects. In our project all technical feasibility are followed because of technical
requirement are fulfilled due to the software and hardware
2.1.2 Operational Feasibility
Operational Feasibility is a measure of how well a proposed system solves the
problem, and takes advantage of the opportunities identified during scope definition
and how it satisfies the requirements identified in the requirement analysis phase of
system development. In our project all operational feasibility as followed due to the
all problems in existing system is solved in the proposed system.
2.1.3 schedule Feasibility
Schedule feasibility defined as the probability of a project to be completed within its
scheduled time limits, by a planned due date. If project has a high probability to be
completed on-time, then its schedule is appraised as high.
2.1.4 Cost Feasibility
The costing feasibility of the project can be estimated using current estimation
models such as lines of code, which allows us to estimate cost as a function of size.

6
Thus, this also allows us to estimate and analyze the feasibility of competition of the
system in the Given time frame. This allows us to have a realistic estimate as well as
a continuous evaluative perspective of the progress of the project.

2.2 Risk Analysis

Risk analysis involves examining how project outcomes and objectives might change
due to the impact of the risk event.
Once the risks are identified, they are analyzed to identify the qualitative and
quantitative impact of the risk on the project so that appropriate steps can be taken to
mitigate them.
Strategic risks result from errors in strategy, such as choosing a technology that
can’t be made to work.
Operational risk includes risks from poor implementation and process problems
such as procurement, production, and distribution.

2.3 Project Scheduling

For developing the project, we have follows the step of software development life
cycle steps with planning schedule and perform the required task with respect that
planning schedule. As shown in fig. there are 6 phases are defined that are Literature
Survey, Requirement Analysis, Design, Coding, Testing, Documentation and
Deployment. We can manage the project to achieve the schedule by accelerating sum
efforts or modifying approaches to meet.

2.4 Cost Estimation

Total number of people 3
Total number of months actually spend 4
Total Hardware expenses 4000

7
 Chapter3
ANALYSIS

3.1 Functional and Non- functional requirement

3.1.1Functional requirements
define the internal workings of the software: that is, the technical details, data
manipulation and processing and other specific functionality that show how the use
cases are to be satisfied. They are supported by non-functional requirements, which
impose constraints on the design or implementation

3.1.2Non- functional requirement

Non-functional requirements are requirements which specify criteria that can be used
to judge the operation of a system, rather than specific behaviors. This should be
contrasted with functional requirements that specify specific behavior or functions.
Typical non-functional requirements are reliability, scalability, and cost. Non-
functional requirements are often called the abilities of a system. Other terms for
non-functional requirements are "constraints", "quality attributes" and "quality of
service requirements".
3.1.3 Reliability: If any exceptions occur during the execution of the software it
should be caught and thereby prevent the system from crashing.
3.1.4 Scalability: The system should be developed in such a way that new modules
3.1.5 Cost: The cost should be low because a free availability of software package

3.2 Hardware Requirement and Software Requirement

3.2.1 hardware requirement
 Raspberry pi
 SD Card
 Camera

8
3.2.2 software requirement

 Raspbian OS
 Open cv
 Python

3.3 Software requirement specification

SVM and Kmeans algorithm are used to detect the cotton leaf disease. K-means is
clustering algorithm used for image segmentation and SVM algorithm is used for the
Feature extraction and classification of unseen data. We are going to do this
identification and detection of disease by using image processing techniques on the
cotton leaf. Initially Edge detection based Image segmentation is done, and finally
image analysis and classification of diseases is performed using our proposed
Homogeneous Pixel Counting Technique for Cotton Diseases Detection (HPCCDD)
Algorithm.

The goal of this research work is identify the disease affected part of cotton
leaf sport by using the image analysis technique. This work find out the computer
systems which analyze the input images using the RGB pixel counting values
features used and identify disease wise and next using homogenization techniques
Sobel and Canny using edge detection to identify the affected parts of the leaf spot to
recognize the diseases boundary is white lighting and then result is recognition of the
diseases as output. detection of leaf diseases has been used method is threefold: 1)
identifying the infected object based upon k-means clustering; 2) extracting the
features set of the infected objects using color co-occurrence methodology for
texture analysis; 3) detecting and classifying the type of disease using CNN.

9
 Chapter 4

Design

4.1 System Architecture

Fig. shows the proposed architecture of experiment ,In this fig there are steps that we
are going to use for cotton leaves disease detection. Firstly, image acquisition than
image processing, image segmentation, feature extraction, and then finally detection
and classification of plant disease.

10
4.1.1Image Acquisition: The images of the plant leaf are gathering from CICR
Nagpur. This image is in RGB form. Color transformation structure for the RGB leaf
image is created, and then, a device-in dependent color space transformation for the
color transformation structure is applied.

4.1.2 Image Pre-processing: To remove noise in image or other object removal,

different pre-processing techniques is consider. Image clipping i.e. cropping of leaf
image to get the interested image region. Image smoothing is done using the
smoothing filter . Image enhancement is carried out for increasing the contrast.

4.1.3 Image Segmentation: Segmentation means partitioning of image into various

parts of same features or having some similarity. The segmentation can be done
using various methods like Otsu’ method, k-means clustering, converting RGB
image into HIS model.

4.1.4 Feature Extraction: Feature extraction plays an important role for

identification of an object. In many application of image processing feature
extraction is used. Color, texture, morphology, edges etc. is the feature which can be
use in plant disease detection

11
4.2 Data Flow Diagram

Input Image

Pre-processing

Disease segmentation

Feature Extraction

Classification

Predict Disease

12
4.3 UML Diagram

13
 Chapter 5

CONCLUSIONS AND FUTURE WORK

5.2 Conclusions

Internet of Things has enables the agriculture crop monitoring easy and efficient to
enhance the productivity of the crop and hence profits for the farmer. Wireless
sensor network and sensors of different types are used to collect the information of
crop conditions and environmental changes and these information is transmitted
through network to the farmer/devices that initiates corrective actions. Farmers are
connected and aware of the conditions of the agricultural field at anytime and
anywhere in the world. Some disadvantages in communication must be overcome by
advancing the technology to consume less energy and also by making user interface
ease of use.

5.1 Future Work

Farmer will get direct information about infected leaf on their phones without
actually going to the leaf , not also cotton but all other leaf diseases also get detected
by this system. We hope that this will happen soon .farmers are not to be worried
about the diseases and pesticides they will become smart farmer onwards after this.

14
 Bibliography
[1] BalajiBhanu, Raghava Rao, J.V.N. Ramesh and Mohammed Ali hussain,
“Agriculture Field Monitoring and Analysis using Wireless Sensor Networks
for improving Crop Production”, 2014 Eleventh International Conference on
Wireless and Optical Communications Networks (WOCN)

[2] LIU Dan, Cao Xin, Huang Chongwei, JI Liang Liang, “Intelligent agent
greenhouse environment monitoring system based on IOT technology”, 2015
International Conference on Intelligent Transportation, Big Data & Smart
City

[3] JosephHaule, Kisangiri Michael, “Deployment of wireless sensor networks

(WSN) in automated irrigation management and scheduling systems: a
review”, Science, Computing and Telecommunications (PACT), 2014, Pan
African Conference

[4] S. Vijayakumar, J. Nelson Rosario, “Preliminary Design for Crop

Monitoring Involving Water and Fertilizer Conservation Using Wireless
Sensor Networks”, Communication Software and Networks (ICCSN), 2011
IEEE 3rd International Conference.

[5] G. Nisha, J.Megala, “Wireless Sensor Network Based Automated Irrigation

and Crop Field Monitoring System”, 2014 Sixth International Conference on
Advanced Computing (IcoAC).

[6] MengJi-hua, Wu Bing-fang, Li Qiang-zi, “A Global Crop Growth

Monitoring System Based on Remote Sensing”, 2006 IEEE International
Symposium on Geoscience and Remote Sensing.

15
[7] Alan Mainwaring, Joseph Polastre, Robert Szewczyk, David Culler, John
Anderson, “Wireless Sensor Networks for Habitat Monitoring”, International
Conference .

[8] Lei Xiao, LejiangGuo, “The Realization of Precision Agriculture

Monitoring System Based on Wireless Sensor Network”, 2010 International
Conference on Computer and Communication Technologies in Agriculture
Engineering.

[9] Ling-ling LI, Shi-feng YANG, Li-yan WANG, Xiang-ming GAO, “The
Greenhouse Environment Monitoring System Based on Wireless Sensor
Network Technology”, Proceedings of the 2011 IEEE International
Conference on Cyber Technology in Automation, Control, and Intelligent
Systems, March 20-23, 2011, Kunming, China.

[10] Chun-ling Fan, Yuan Guo, “The Application of a ZigBee Based Wireless
Sensor Network in the LED Street Lamp Control System”, 2013, College of
Automation & Electronic Engineering, Qingdao University of Scientific &
Technology, Qingdao, China embedded technology, Consumer Electronics -
China, 2014 IEEE International Conference.

16
 PLAGIARISM SCAN REPORT

Words 146 Date January 12,2021

Characters 910 Exclude URL

0% 100% 0 7
Plagiarized
Plagiarism Unique Unique Sentences
Sentences

Content Checked For Plagiarism

The large number of individuals depends on cotton crop. the popularity of cotton disease
are of the most important as they have a cogent and momentous impact on quality and
production of cotton. Cotton disease identification is an art and science. Now a day’s
image processing technique becoming a key technique for diagnosing the many features
of the crop. This paper mainly focuses detection of varied cotton crop diseases and to
classify them.
There are classification techniques like k-Nearest classifier , k-means Clustering. A sensible
phone empowers farmer to stay updated with the going conditions of his agricultural land
using IOT at any time and any part of the planet. IOT technology can reduce the value and
enhance the productivity of traditional farming, not every farmer buy smart phone they
mainly focuses on the crops growing, there is a lagging thing in most of the farmers.

Sources Similarity