Project Report PDF

IDENTIFICATION OF LEAF DISEASES USING IMAGE PROCESSING
A PROJECT SEMINAR REPORT ON
IDENTIFICATION OF LEAF DISEASES USING IMAGE

PROCESSING
BY
Name Roll No.

Yash Girish Magar B150243065
Sachin Deorao Ghodke B150243046
Atul Kailas Khedkar B150243140
UNDER THE GUIDANCE OF

Prof. Smita Desai
IN PARTIAL FULFILLMENT OF
B.E. (ELECTRONICS & TELECOMMUNICATION)
DEGREE OF SAVITRIBAI PHULE PUNE UNIVERSITY

OCT/NOV-2018
DEPERTMENT OF ELECTRONICS & TELECOMMUNICATION
Dr. D. Y. Patil Vidya Pratishthan Society’s

DR. D.Y.PATIL INSTITUTE OF TECHNOLOGY,
PIMPRI, PUNE – 41101
DIT, PIMPRI 2018-19 Page 1

Dr. D. Y. Patil Vidya Pratishthan Society’s

DR. D. Y. PATIL INSTITUTE OF TECHNOLOGY,
PIMPRI, PUNE – 411018
CERTIFICATE
This is to certify that the project entitled “IDENTIFICATION OF LEAF DISEASES USING
IMAGE PROCESSING” submitted by
Yash Girish Magar (B150243065)

Sachin Deorao Ghodke (B150243046)
Atul Kailas Khedkar (B150243140)
Is record of bonafide work carried out by them under my guidance, in partial fulfillment of
Project phase 1 of Final Year Engineering ( Electronics & Telecommunication) of Savitribai
Phule Pune University.
Date:
Place: Dr. D.Y.P.I.T., Pimpri, Pune-18
Prof. Smita Desai Dr. S. R. Jog Dr. S. N. Mali

Project Guide H.O.D. Principal

ACKNOWLEDGEMENT
We express our sincere thanks to our Project Guide Prof. Smita Desai for her encouragement and
support throughout our project, especially for the useful suggestions given during the course of
project and having laid down the foundation for the success of this work.
We would also like to thank our Project Coordinator Prof. Nilakshee Bagdure for her assistance,
genuine support and guidance from early stages of the project. We also thank Principal Dr. S.N.
Mali & Dr. S.R. Jog, Head of the Department of Electronics and Telecommunication
Engineering for their unwavering support during the entire course of this project work. We also
thank all the staff members of our department and technicians for their help in making our project
report work successful.
I also wish to convey our gratitude to our friends for their constant encouragement and help
without which this project would not be possible.

CONTENTS
ABSTRACT…………………………………………………………………………………… i
LIST OF TABLES…………………………………………………………………………….. ii
LIST OF FIGURES…………………………………………………………….......…………. iii
Chapter No. Name of Chapter Page No.
Chapter 1. INTRODUCTION AND LITERATURE SURVEY

1.1 Introduction
1.2 Research Motivation
1.3 Literature Survey
Chapter 2. SYSTEM SPECIFICATIONS & BLOCK SCHEMATIC

2.1 System Specifications
2.2 Block Schematic
2.3 Working Principle
Chapter 3. HARDWARE DESIGN/TECHNICAL DETAILS

3.1 Hardware Design
3.2 Circuit Design
3.3 Circuit Layout Design
Chapter 4. SOFTWARE DESIGN

4.1 Algorithm
4.2 Flowchart
Chapter 5. TEST SETUP AND TESTING PROCEDURE

5.1 Test Setup
5.2 Testing Procedure
Chapter 6. RESULT AND ANALYSIS
Chapter 7. APPLICATIONS
Chapter 8. CONCLUSION AND FUTURE SCOPE
BILL OF MATERIAL
REFERENCES/BIBLIOGRAPHY

Abstract
Producing agricultural products are difficult task as the plant comes to an attack from various
micro-organisms, pests and bacterial diseases. Image processing techniques can be used in
performing early detection of plant diseases through leaf features inspection. Leaf image is
captured and then processed to determine the status of plant. Proposed frame work model into
four parts. Image pre-processing including RGB to different color space conversion. Image
enhancement, segment the region of interest using K-mean clustering for statistical usage to
determine the defect and severity areas of plant leaves, feature extractionand classification.
Texture feature extraction is done using GLCM (gray-level co-occurrence matrix) and colour
features by means of mean values. Finally classification can be achieved using SVM (support
vector machine. This will ensure that chemicals only applied when plant leaves are detected to be
effected with the disease.

List of Figures
Figure No. Figure Title

1 Infected Leaves
2 Block Diagram
3 Working Principle
4 GSM module
5 Web camera
6 Flowchart
7 Testing Procedure
8 Result analysis

CHAPTER 1. INTRODUCTION AND LITERATURE SURVEY

1.1 Problem Definition
One of the important sectors of Indian Economy is Agriculture. Employment to almost 50% of
the countries workforce is provided by Indian agriculture sector. India is known to be the world's
largest producer of pulses, rice, wheat, spices and spice products. Farmer's economic growth
depends on the quality of the products that they produce, which relies on the plant's growth and
the yield they get. Therefore, in field of agriculture, detection of disease in plants plays an
instrumental role. Plants are highly prone to diseases that affect the growth of the plant which in
turn affects the ecology of the farmer. In order to detect a plant disease at very initial stage, use of
automatic disease detection technique is advantageous. The symptoms of plant diseases are
conspicuous in different parts of a plant such as leaves, etc. Manual detection of plant disease
using leaf images is a tedious job. Hence, it is required to develop computational methods which
will make the process of disease detection and classification using leaf images automatic..
1.2 Introduction
Agriculture is not only to feed ever growing population but it’s also important source of energy.
Plant diseases affect both quality and quantity of crops in agriculture production. Plant disease
diagnosis is very essential in earlier stage in order to prevent and control them. The naked eye
observation of experts is the main approach adopted in for detection and identification of plant
diseases. But the naked eye observation is time consuming, expensive and take lots of efforts.
To remove drawbacks in existing system many system have been proposed to overcome those
drawbacks by using different techniques. In the next section this paper tries to present those
proposed systems in meaningful way. The management of crops required close inspection
especially for management of disease infected crop that can affect the quality and quantity of
crop. Image processing is an best technique for agricultural application. Image processing can
detect an pest’s attack from the image of plant. The detection and classification of plant diseases
are important task to increase plant productivity.

There are various techniques emerged to detect the plant disease such as thresholding, region
growing, clustering, Edge based detection etc. To detect plant disease the image should go
through some process like pre-processing, segmentation, feature extraction and classification
processes. The pre-processing is an improvement process of image data to suppresses unwanted
distortion or enhances some image features important for further processing.
The segmentation process is to partition an image into meaningful regions and it is vital process
through which image features are extracted. There are various features of an image such as grey
level, color, texture, shape, depth, motion, etc. Classification process is used to classify the given
input data into number of classes and groups. It classifies the data based upon selected features.
Figure 1: Infected Leaves

1.3 Literature Survey

In this section we discussed the different methods proposed for leaf disease detection
published in between 2011 to 2016.
Sanjay B. Patil et.al (2011)

In [13], author proposed the Triangle threshold and simple threshold methods. These methods
are used to lesion region area and segment the leaf area respectively. In final step, categorization
of disease is done by calculating the quotient of leaf area and lesion area. According to the
research done, the given method is fast and accurate for calculating leaf disease severity and leaf
area calculation is done by using threshold segmentation.
Mrunalini R. Badnakhe et.al (2011)

In [9], author presented the technique to classify and identify the different disease through which
leafy vegetables are affected. In Indian Economy a Machine learning based recognition system
will proves to be very useful as it saves efforts, money and time too. The approach given in this
for feature set extraction is the Color Co-occurrence Method. For automatic detection of
diseases in leaves, neural networks are used. The approach proposed can significantly support an
accurate detection of leaf, and seems to be important approach, in case of steam, and root
diseases, putting fewer efforts in computation.
Anand H. Kulkarni et al. (2012)

In [11], author introduced methodology for early and accurately plant diseases detection, using
artificial neural network (ANN) and diverse image processing techniques. As the proposed
approach is based on ANN classifier for classification and Gabor filter for feature extraction, it
gives better results with a recognition rate of up to 91%. An ANN based classifier classifies
different plant diseases and uses the combination of textures, color and features to recognize
those diseases.

Murali Krishnan et.al (2013)
In [3], novel algorithm for detecting bacterial leaf scorch of shade trees using image
processing concepts is proposed. The method of this paper uses a novel approach to detect
the infected areas of the plant by segmenting the plant leaves by clustering. K-means
clustering was performed for different cluster centres to obtain different cluster groups
of the region of interest (ROI).
Muhammad Thaqif bin MohamadAzmi et.al (2013)

In [1], author proposed an orchid disease detection system using image processing and fuzzy
The goal of author in this paper was to present system that is able to detect an orchid disease
by processing its leaf image. The system consists of two parts, image processing and fuzzy
logic. The leaf image processing used methods are like grayscaling, threshold segmentation
and noise removing. The data collected from the image processing were the centroid, area and
number of diseased spot. These data or numbers were then fed through the fuzzy logic system
to be processed through fuzzification, fuzzy inference and defuzzification in order to get the
output. Sanjay B.
Dhaygude et.al (2013)

In [8], there are mainly four steps in developed processing scheme, out of which, first one is,
for the input RGB image, a color transformation structure is created, because this RGB is used
for color generation and transformed or converted image of RGB, that is, HSI is used for color
descriptor. In second step, by using threshold value, green pixels are masked and removed. In
third, by using precomputed threshold level, removing of green pixels and masking is done for
the useful segments that are extracted first in this step, while image is segmented. And in last
or fourth main step the segmentation is done.
S. Arivazhagan et.al (2013)

In [10], another approach for diseased detection proposed. According to [4] disease
identification process include some steps out of which four main steps are as follows: first, for
the input RGB image, a color transformation structure is taken, and then using a specific

threshold value, the green pixels are masked and removed, which is further followed by
segmentation process, and for getting useful segments the texture statistics are computed. At
last, classifier is used for the features that are extracted to classify the disease. The proposed
algorithm shows its efficiency with an accuracy of 94% in successful detection and
classification of the examined diseases. The robustness of the proposed algorithm is proved by
using experimental results of about 500 plant leaves in a database.
Smita Naikwadi et.al (2013)

In [12], histogram matching was used to identify plant disease. In leafy vegetables, disease
appears on leaf therefore the histogram matching is done on the basis of edge detection
technique and color feature. Layers separation technique is used for the training process which
includes the training of these samples which seperates the layers of RGB image into red, green,
and blue layers and edge detection technique which detecting edges of the layered images.
Spatial Gray-level Dependence Matrices are used for developing the color cooccurrence
texture analysis method.
Jagadeesh D. Pujari et.al (2014)

In [6], author intorduced a study on the image processing techniques used to identify and
classify fungal disease symptoms affected on different agriculture/horticulture crops. Four
different classes of agriculture/horticulture crops: fruit crops, vegetable crops, commercial
crops, and cereal crops affected by fungal disease were used for the considered work.
Algorithms for feature extraction and classification based on image processing techniques
were designed for each crop separately. Authors aimed at development of methodology for
identification and classification of fungal disease symptoms affected on horticulture and
agriculture crops.
Amandeep Singh et. al (2015)

In [2], author introduced method for color prediction of paddy crop leaf using image
processing. They designed the method which may be used to compare the crop leaf color with
the leaf color chart (LCC), has been proposed for getting a detail about the requirement of
plant, before enough to get the yield affected. By making use of image processing technology a

simple and robust method for the color prediction of paddy crop plant has been discussed
along with the mathematical modelling which may provide a great platform to the advisory
bodies in the agriculture field for the atomization of the crop health problems and solutions.
Dhiman Mondal et.al (2015)

In [4], proposed an efficient technique to detect and classify the presence of Yellow Vein
Mosaic Virus (YVMV) disease in okra leaf with the joint use of image processing, K-means
and Naive Bayesian classifier. The proposed technique was experimented on 79 standard
diseased and non diseased okra leaf images. The input leaf images were of four classes,
namely Highly Susceptible (HS), Moderately Susceptible (MS), Tolerable (T) and Resistive
(R), depending upon the severity of the YVMV infection.
Sachin D. Khirade et.al (2015)

In [5], author proposed another approach for plant disease detection based on image
processing. This paper discussed the methods used for the detection of plant diseases using
their leaves images. This paper also discussed some segmentation and feature extraction
algorithm used in the plant disease detection. This is nothing but the introductory research
article presented by author.
Vijai Singh et.al (2015)

In [7], author proposed an algorithm for image segmentation technique used for automatic
detection as well as classification of plant leaf diseases and survey on different diseases
classification techniques that can be used for plant leaf disease detection. Image segmentation,
which is an important aspect for disease detection in plant leaf disease, was done by using
genetic algorithm. This paper gives the survey on different diseases classification techniques
that can be used for plant leaf disease detection and an algorithm for image segmentation
technique used for automatic detection as well as classification of plant leaf diseases has been
described later. Banana, beans, jackfruit, lemon, mango, potato, tomato, and sapota are some
of those ten species on which proposed algorithm was tested by author.

CHAPTER 2. SYSTEM SPECIFICATION & BLOCK SCHEMATIC
2.1 System Specification :
- Through GSM disease detection report is send via SMS.

- Windows OS 7 or Onwards.
- MATLAB R2010a.
- WEB cam to capture the clear image.
2.2 Block Schematic :
As shown in below block diagram laptop is been used to process matlab into which leaf disease
detection algorithm is implemented, leaf disease algorithm detects diseases and passes command
to GSM via pl2303 usb to serial converter . thisAT commands allow GSM to send message to
particular user in which disease name and solution is main content
Matlab Usb to serial gsm

(laptop) converter
Figure 2: Block Diagram

2.3 Working Principle :
The block diagram of the proposed system is shown in below fig The step by step proposed
approach consists of leaf and fruit image database collection, pre-processing of those images,
segmentation of those images using k-means clustering method, feature extraction using texture
information method and finally the training of system using cross correlation algorithm.
Figure 3: Working principle

CHAPTER 3. HARDWARE DESIGN/TECHNICAL DETAILS
3.1 Hardware design:
The system design comprises of :
GSM Module:
The SIM900A is a readily available GSM/GPRS module, used in many mobile phones and
PDA. The module can also be used for developing IOT (Internet of Things) and Embedded
Applications. SIM900A is a dual-band GSM/GPRS engine that works on frequencies EGSM
900MHz and DCS 1800MHz. SIM900A features GPRS multi-slot class 10/ class 8 (optional) and
supports the GPRS coding schemes CS-1, CS-2, CS-3 and CS-4.
Figure 4: GSM Module
Features:
o Single supply voltage: 3.4V – 4.5V.

o Power saving mode: Typical power consumption in SLEEP mode is 1.5mA.

o Frequency bands:SIM900A Dual-band: EGSM900, DCS1800. The SIM900A can search

the two frequency bands automatically. The frequency bands also can be set by AT
command.
o GSM class: Small MS.
o GPRS connectivity: GPRS multi-slot class 10 (default) , GPRS multi-slot class 8 (option).
o Transmitting power: Class 4 (2W) at EGSM 900, Class 1 (1W) at DCS 1800.
o Operating Temperature: -30ºC to +80ºC.
o Storage Temperature: -5ºC to +90ºC.
o DATA GPRS: download transfer max is 85.6KBps, Upload transfer max 42.8KBps.
o Supports CSD, USSD, SMS, FAX.
o Supports MIC and Audio Input.
o Speaker Input.
o Features keypad interface.
o Features display interface.
o Features Real Time Clock.
o Supports UART interface.
o Supports single SIM card.
o Firmware upgrade by debug port.
o Communication by using AT commands.
Web Camera
Figure 5: Web Camera

Connection Type Corded USB

USB Type High Speed USB 2.0
USB VID_PID VID_046D&PID_081A
Microphone Built-in, Noise Supression
Lens and Sensor Type Plastic
Focus Type Fixed
Field of View (FOV) 60°
Focal Length 4.0 mm
Optical Resolution (True) 1280 x 960 1.2MP
Image Capture (4:3 SD) 320x240, 640x480 1.2 MP, 3.0 MP
Image Capture (16:9 W) 360p, 480p, 720p
Video Capture (4:3 SD) 320x240, 640x480, 800x600
Video Capture (16:9 W) 360p, 480p, 720p,
Frame Rate (max) 30fps @ 640x480
Video Effects (VFX) N/A
Right Light Right Light 2
Buttons Other NA
Indicator Lights (LED) Activity/Power
Privacy Shade No
Clip Size (max) 0 to infinity
Cable Length 5 Feet or 1.5 Meters

CHAPTER 4. SOFTWARE DESIGN
4.1 Algorithm:
Step 1 : Start.
Step 2:insert sim in gsm module
Step 3: Initialize system.
Step 4 : Wait for establishment of network connection.
Step 5 : scan leaf image through camera.
Step6:localize the leaf in image.
Step7:segment the affected area in leaf if any
Step8:extract the information .
Step 9: compare heck for threshold value and take the decision if input image of leaf is healthy
or diseased.
Step 10 : result is send through gsm via sms.
Step 11 : Stop.

4.2 Flowchart
Figure 6: Flowchart

CHAPTER 5. TEST SETUP AND TESTING PROCEDURE
5.1 Test set up:
GSM Test Setup

1) Insert SIM card
Open the SIM cardholder by sliding it as per the arrow mark and lit up. Insert the SINI card, so s
to align the chamfered corner suits in card holder. After inserting the SIM card, lock the holder by
sliding it to the opposite direction of arrow mark.
2) Connect the Antenna

Fix the Supplied RF antenna to the SMA Antennae connector and tighten it by Rotating the Nut
(Never rotate the antennae for tightening).
3) Connect the Pins

Connect the GSM modem as per the circuit diagram provided.
4) Power the Modem

Power the modem from suitable power supply, which is having enough current capacity(>1A).
5) Check the Status of the LEDS

PWR LED Red LED will lit immediately
STS LED Green LED will lit after 1-2 seconds
NET LED -Blue LED will starts to blink in fast for few seconds (Searching ForNetwork) and
becomes slow blinking once the Modem registers with the Network.
6) Network LED
The Network LED indicates the various status of GSM module e.g. Power on,
Network registration & GPRS connectivity. When the modem is powered up, the status LED
will blink every second. After the Modem registers in the network (takes between 10-60 seconds),
LED will blink in step of 3 seconds. At this stage you can start using Modem for your application.

7) Baud rate
The Baud rate supported by the modem 1s between 9600 and 115200. Make sure the
host system is set to the supported baud rate.
The modem automatically sets to the baud rate of the first command sent by the host
system after it is powered up. User must first send "A" to synchronize the baud rate. It is
recommended to wait 2 to 3 seconds before sending "AT" character. After receiving the
OK" response, Your Device and GSM Modem are correctly synchronized. So there is no
need for setting the baud rate using commands. Before You Start using the modem, please make
sure that the SIM card you inserted support the needed features and there is enough
balance in SIM.

5.2 Testing Procedure
In this chapter we study about the whole project hardware and then after we check the hardware
by using the multimeter. If there is an error in the hardware then by using the continuity tester we
check the track connection path of hardware. Sometimes there are many erors are occurs we have
tested them by following way:
• Firstly check the connection of circuit diagram as per the connection on proteus software.
• Second by using the ARES we make a layout of circuit diagram and check the tracing path
of circuit with respect to ground
• Third we add software program in our simulation circuits and check out the interlacing of
hardware and software.
• Then debugging the program step by step and get desire output voltage at the pin of GSM.
• Then check out all solder connection. Check whether there is short connection or not.
Also check the supply voltage of each stage in running mode.
Figure 7: Testing Procedure

CHAPTER 6. RESULT AND ANALYSIS
Figure 8: Result Analysis
As discussed in the introduction, solution is composed of four phases.In this, input image is
selected from dataset folder as shown in Figure 2. Color transformation structure is created. Then
color based segmentation is applied to get the infected region of interest. The choice of selection
of number of clusters is user dependent. This is the region of interest for further processing.
Infected cluster is selected. Green pixels are masked based on threshold value set. Also Pixels on
the boundaries are also removed as they both do not contribute to disease identification process.

CHAPTER 7. APPLICATIONS
• Agricultural
Image information can play a crucial role in the diagnosis of different diseases in the
agricultural domain where the understanding of image symptoms is often essential to
problem solving. Vegetable crops suffer from many leaf batches. Leaf batches differ in
color, shape and size according to the cause. Leaf batches happen as a result of plant
pathogens (Fungi, Bacteria and viruses), insect feeding (sucking insect pastes), and plant
nutrition (lack of microelements). The importance of the fungal diseases came from its
great distribution, short life cycle and propagation. In agricultural mass production, it is
needed to discover the beginning of plant diseases batches early to be ready for
appropriate timing control to reduce the damage production costs and increase the income.
Plant leaves are considered first station for the rest and germination of bacterial, fungal
capsules due to suitable macro environment.
• Medicinal plant recognition.
Identification of the correct medicinal plants that goes in to the preparation of a medicine
is very important in ayurvedic medicinal industry. The main features required to identify a
medicinal plant is its leaf shape, colour and texture. Colour and texture from both sides of
the leaf contain deterministic parameters to identify the species.
A database of medicinal plant leaves is created from scanned images of front and back
side of leaves of commonly used ayurvedic medicinal plants. The leaves are classified
based on the unique feature combination. Identification rates up to 99% have been
obtained when tested over a wide spectrum of classifiers. The above work has been
extended to include identification by dry leaves and a combination of feature vectors is
obtained, using which, identification rates exceeding 94% have been achieved.

• Biological research.
Images form important data and information in biological sciences. Until recently
photography was the only method to reproduce and report such data. It is difficult to
quantify or treat the photographic data mathematically. Digital image processing and
image analysis technology based on the advances in microelectronics and computers
circumvent these problems associated with traditional photography. This new tool helps to
improve the images from microscopic to telescopic range and also offers a scope for their
analysis. It, therefore, has many applications in biology (Sainis, et al., 1994). However, as
is the case with any new technology, imaging technology also has to be optimised for each
application, since what each user is looking for in an image is quite unique. Bhabha
Atomic Research Centre (BARC) is a multidisciplinary research institute with advanced
research programmes in many fields of science and technology including electronics and
computer sciences on one-hand and biology and agriculture on the other. BARC is,
therefore, an ideal place for developing the uses of image processing technology in many
scientific disciplines including biology and agriculture.

CHAPTER 8. CONCLUSION AND FUTURE SCOPE
8.1 Conclusion:
The detection of plant disease is one of the important tasks. A plant disease reduces the
production of agriculture. Every year the loss due to various diseases is challenging part in
Agriculture production. Although work is carried out till time on detection of diseases but proper
segmentation of affected part based on type of plant family is still an open problem as a research
area.
8.2 Future Scope:
Using different technologies and method we can make faster efficient application.
In order to increase the future scope of the disease detection large datasets of different disease
should be used.
In the future, the proposed methodology can be integrated with other yet to be developed,
methods for disease identification and classification using color and texture analysis to develop an
expert system for early soya plant foliar disease warning and administration, where the disease
type can be identified by color and texture analysis and the severity level estimation by our
proposed method since it is disease independent. The performance of the system can be improved
in the future by using advanced background separation methods to separate the leaf object from a
complex background. More infections like downy mildew (DM) and sudden death syndrome
(SDS) can also be classified along with the BB, FE, BS, and SR by using the proposed ST-NDCT
based cataloguing algorithm, but due to non-availability of suitable and sufficient training and test
data at present it has not been incorporated into the present work. The similar methodology can be
applied to other plant foliar infections and early warning systems for - 165 - rice, cotton-crops,
fruits, vegetables and beans, etc. The use of other cataloguing methods can be exploited to
improve the accuracy of the system in future.

REFERENCES
[1] Muhammad Thaqif bin MohamadAzmi, Naimah Mat Isa, “Orchid Disease Detection Using
Image Processing and Fuzzy Logic”, 2013 International Conference on Electrical, Electronics
and System Engineering, IEEE.
[2] Amandeep Singh, Maninder Lal Singh, “Automated Color Prediction of Paddy Crop Leaf
using Image Processing”, 2015 IEEE International Conference on Technological Innovations
in ICT for Agriculture and Rural Development (TIAR 2015).
[3] Murali Krishnan, Dr.M.G.Sumithra, “A Novel Algorithm for Detecting Bacterial Leaf
Scorch (BLS) of Shade Trees Using Image Processing”, 2013 IEEE 11th Malaysia
International Conference on Communications.
[4] Dhiman Mondal, Dipak Kumar Kole, ““Detection and Classification Technique of Yellow
Vein Mosaic Virus Disease in Okra Leaf Images using Leaf Vein Extraction and Naive
Bayesian Classifier” 2015 International Conference on Soft Computing Techniques and
Implementations- (ICSCTI), IEEE.
[5] Sachin D. Khirade, A. B. Patil, “Plant Disease Detection Using Image Processing”, 2015
International Conference on Computing Communication Control and Automation, IEEE.
[6] Jagadeesh D. Pujari, Rajesh Yakkundimath, Abdulmunaf S.Byadgi, “Identification and

Classification of Fungal disease Affected on Agriculture/Horticulture Crops using Image
Processing Techniques”, 2014, IEEE.
[7] Vijai Singh, Varsha, Prof. A K Misra, “Detection of unhealthy region of plant leaves using
Image Processing and Genetic Algorithm”, 2015 International Conference on Advances in
Computer Engineering and Applications (ICACEA), IEEE.

[8] Prof. Sanjay B. Dhaygude, Mr.Nitin P.Kumbhar “Classifieral plant Leaf Disease Detection
Using Image Processing” International Journal of Advanced Research in Electrical, Electronics
and Instrumentation Engineering Vol. 2, Issue 1, January 2013.
[9] Mrunalini R. Badnakhe and Prashant R. Deshmukh” An Application of K-Means

Clustering and Artificial Intelligence in Pattern Recognition for Crop Diseases”, International
Conference on Advancements in Information Technology 2011 IPCSIT vol.20 (2011).
[10] PiyushChaudhary, Anand K. Chaudhari, Dr. A. N. Cheeran and Sharda Godara, “Color
Transform Based Approch For Disease Spot Detection on Plant Leaf”, International Journal of
Computer Science and Telecommunications, 2012,pp. 65-70.
[11] Ms. Rupali S. Zambre, “Classification of Cotton Leaf Spot Disease Using Support Vector
Machine”, International Journal of Engineering Research and Applications, 2014, pp. 92-97.
[12] P. Revathi and M. Hemalatha, “Advance Computing Enrichment Evaluation of Cotton Leaf
Spot Disease Detection Using Image Edge detection”, IEEE, 2012.
[13] Shiv Ram Dubey, Anand Singh Jalal, “Detection and Classification of Apple Fruit Diseases
using Complete Local Binary Patterns”, International Conference on Computer and
Communication Technology IEEE, 2012, pp. 346-351.
[14] Sanjeev S. Sannakki, Vijay S Rajpurohit, V. B. Nargund and Pallavi Kulkarni, “Diagnosis
and Classification of Grape Leaf Diseases using Neural Networks”, International Conference on
Computing,
[15] http://stackoverflow.com/questions/30022377/what-should-i-use-hsv-hsb-
or-rgb-and-why
[16] http://in.mathworks.com/help/matlab/ref/rgb2hsv.html
[17] Jagadeesh Devdas Pujari, Rajesh Yakkundimath and Abdulmunaf Byadgi, “Grading and
Classification of Anthracnose Fungal Disease of Fruits based on Statistical Texture Features”,
International Journal of Advanced Science
and Technology, 2013, pp. 121-129.

BILL OF MATERIALS
Sr. No. Component Ratings Quantity

Name
1 Camera 480 1
2 GSM module 900 1
Total = 1380/-

Project Report PDF

Uploaded by

Document Informationclick to expand document information

Copyright:

Available Formats

Project Report PDF

Uploaded by

Document Information

Original Title

Copyright

Available Formats

Share this document

Share or Embed Document

Sharing Options

Did you find this document useful?

Is this content inappropriate?

Copyright:

Available Formats

Project Report PDF

Uploaded by

Copyright:

Available Formats

IDENTIFICATION OF LEAF DISEASES USING IMAGE PROCESSING

A PROJECT SEMINAR REPORT ON

IDENTIFICATION OF LEAF DISEASES USING IMAGE

Name Roll No.

UNDER THE GUIDANCE OF

DEGREE OF SAVITRIBAI PHULE PUNE UNIVERSITY

DEPERTMENT OF ELECTRONICS & TELECOMMUNICATION

Dr. D. Y. Patil Vidya Pratishthan Society’s

DIT, PIMPRI 2018-19 Page 1

Dr. D. Y. Patil Vidya Pratishthan Society’s

Yash Girish Magar (B150243065)

Prof. Smita Desai Dr. S. R. Jog Dr. S. N. Mali

DIT, PIMPRI 2018-19 Page 2

DIT, PIMPRI 2018-19 Page 3

Chapter No. Name of Chapter Page No.

Chapter 1. INTRODUCTION AND LITERATURE SURVEY

Chapter 2. SYSTEM SPECIFICATIONS & BLOCK SCHEMATIC

Chapter 3. HARDWARE DESIGN/TECHNICAL DETAILS

Chapter 4. SOFTWARE DESIGN

Chapter 5. TEST SETUP AND TESTING PROCEDURE

Chapter 6. RESULT AND ANALYSIS

Chapter 8. CONCLUSION AND FUTURE SCOPE

DIT, PIMPRI 2018-19 Page 4

DIT, PIMPRI 2018-19 Page 5

Figure No. Figure Title

DIT, PIMPRI 2018-19 Page 6

CHAPTER 1. INTRODUCTION AND LITERATURE SURVEY

DIT, PIMPRI 2018-19 Page 7

Figure 1: Infected Leaves

DIT, PIMPRI 2018-19 Page 8

1.3 Literature Survey

Sanjay B. Patil et.al (2011)

Mrunalini R. Badnakhe et.al (2011)

Anand H. Kulkarni et al. (2012)

DIT, PIMPRI 2018-19 Page 9

Murali Krishnan et.al (2013)

Muhammad Thaqif bin MohamadAzmi et.al (2013)

Dhaygude et.al (2013)

S. Arivazhagan et.al (2013)

DIT, PIMPRI 2018-19 Page 10

Smita Naikwadi et.al (2013)

Jagadeesh D. Pujari et.al (2014)

Amandeep Singh et. al (2015)

DIT, PIMPRI 2018-19 Page 11

Dhiman Mondal et.al (2015)

Sachin D. Khirade et.al (2015)

Vijai Singh et.al (2015)

DIT, PIMPRI 2018-19 Page 12

CHAPTER 2. SYSTEM SPECIFICATION & BLOCK SCHEMATIC

2.1 System Specification :

- Through GSM disease detection report is send via SMS.

2.2 Block Schematic :

Matlab Usb to serial gsm

Figure 2: Block Diagram

DIT, PIMPRI 2018-19 Page 13

2.3 Working Principle :

Figure 3: Working principle

DIT, PIMPRI 2018-19 Page 14