Leaf Disease Detection and Prevention Using Image Processing

using Matlab
Prajakta Mitkal1, Priyanka Pawar2, Mira Nagane3, Priyanka Bhosale4,
Mira Padwal5 and Priti Nagane6
1,2
Computer Engineering, Karmayogi Engg College, Shelve, Pandharpur

Abstract— Nowadays many of the farmers and agro help center use the different new technology to
enhance the agriculture production. Plants have become important source of energy. There are
several diseases that affect plants with the potential to cause economic and social losses. Many of
disease are most popular where disease spots occur on the sugar cane plant leaves. If the disease are
not detected at first stage than it is more harm full to production. To find out particular disease using
Digital image processing helps to find disease and provide prevention for particular disease which
types pesticide need to prevent disease. Firstly take Input image in RGB form then the green pixels
are removed then the image is segmented useful segment used for extraction finally texture statistics
is completed and according to analysis disease prevention is provided.
Keywords— Digital image processing; segmentation; Extraction; Agriculture Production; Spots;
Sugarcane.
I. INTRODUCTION
Agriculture is changing social and economic environment day today. Improper management
leads to loss in agricultural products [1]. Farmers lack the knowledge of disease and hence they
produce less production. Kisan call centres are available but do not service 24*7 and sometimes
communication will be fail. Farmers are not able to explain disease properly on call need to analysis
the image of affected area of disease. Images and videos of crops provide better view and agro
scientist can provide a better solution but it not getting to all farmers. The experimental results
indicate that the proposed approach is a valuable approach, which can significantly support an
accurate detection of leaf diseases in a less computational effort.
1.1 Image Processing
In today’s modern digital world research are continuously trying to increasing the collectively
of plants [1]. They have archived by using developing the higher breed seeds and plants. But one
problem still exist which is a major concern of the cultivation of crop and that is crop diseases and
the pesticides problem. Due to these problems, the cultivation decreases and hence all the farmers
and in turn the country suffers the lack of cultivation of plant [2]. Many of the time disease need to
prevent at early stage, but it not happens then it damage the plants [3][4]. Due to that whatever the
investment need to do that also in loss, to avoiding all these need to detect disease at early stages.
Sugarcane is cultivated in long duration that is 10 to 18 months, that leads to attack of many diseases
[5]. Fungi-caused diseases in sugarcane are the most predominant disease that appears as spots on the
leaves.
In case of severe infection, the leaf become totally covered with diseased spots, disease
determines the quantity, quality, stability of yield. Excessive use of pesticides increase the danger of
toxic residue level on products it has been identified as a major contributor to ground water
contamination now days pesticides price are increasing day by day. To achieve highest production
with less cost they need to use modern technique to enhance productivity with minimum time more
profit [1].

@IJRTER-2016, All rights Reserved 26

 International Journal of Recent Trends in Engineering & Research (IJRTER)
Volume 02, Issue 02; February– 2016 [ISSN:2455-1457]
We are taken 6 type of disease as experimental model for detection.
a. Brown Spot.
b. Downy mildew
c. Sugarcane Mosaic
d. Red stripe
e. Red rot
f. Downy Fungal
1.2 Algorithm
The algorithms that work on feature extraction are as:
a. Linear SVM
b. Non Linear SVM
c. Multiclass SVM

Let us discuss these algorithms in detail as follows:

1.2.1 Linear SVM:
Maximum margin hyper plane and margins for an SVM trained with samples from two classes.

Fig. 1 Hyperplanes in Linear SVM

1.2.2 Non Linear SVM:

This allows the algorithm to fit the maximum-margin hyper plane in a transformed feature space.

Fig. 2 Kernel machines used in Nonlinear SVM for comparison

1.2.3 Multiclass SVM:

Multiclass SVM aims to assign labels to instances by using support vector machines, where
the labels are drawn from a finite set of several elements. In machine learning, support vector
machines are supervised learning models with associated
Learning algorithms that analyze data and recognize patterns, used for classification and
regression analysis.
1.3 Database
Database contained large amount of image samples files which are containing the disease
image and non-disease images. According to Image feature extraction techniques, the features will
be extracted and then that image file will be stored in the database [6].

@IJRTER-2016, All rights Reserved 27

 International Journal of Recent Trends in Engineering & Research (IJRTER)
Volume 02, Issue 02; February– 2016 [ISSN:2455-1457]
II. LITERATURE SURVEY
Following table shows the literature survey:
Table 1 Review of papers

Sr. No Title Author Name and year of Techniques Used

publication
1 Leaf Disease Severity Sanjay B. Patil et al./ Feature Extraction using
Measurement Using International Journal of threshold method and triangle
Image Processing Engineering and thresholding method.
Technology Vol.3 (5),
2011, 297-301
2 Classification of Cotton P.Revathi Research Cotton Diseases Control has
Leaf Spot Diseases Scholar, University been developed in a BP neural
Using Image Coimbatore-21, network as a decision-making
Processing Edge TamilNadu, India,2012 system.
Detection Techniques IEEE.

III. EXISTING SYSTEM

Genetic algorithm (GA) is a powerful searching technique that is used to solve problems in
many different ways. Genetic Algorithm (GA) is efficient search method based on principles of
natural selection and genetics.GA is used to find out the optimal solutions among the search space
with the operators like selection, crossover, mutation, etc. This work presents the methodology for
detecting plant leaf diseases and the way for getting optimal solution of leaf disease detection using
genetic algorithm [1].

IV. PROPOSED APPROACH

These proposed works are more focus on Detection of disease on the sugar cane leaf using
Matlab.
Firstly capture image from digital camera (mobile camera). Most probably the camera with
some limitations and criteria will be considered. The captured image will be considered for further
feature extraction, using one of the above algorithms. There are many features of images that are to
be extracted, but we in our proposed system are going to consider some of them. The below system
architecture shows the actual work flow of the concept that we are working on. The main focus of
this proposed work is to help the farmers, suffering from loss due to incomplete knowledge of
various diseases. The concept should be more user-friendly so, we are focusing on language
translation too. Currently we are focusing on two languages that are English and Marathi.

Fig. 3 System architecture

@IJRTER-2016, All rights Reserved 28

 International Journal of Recent Trends in Engineering & Research (IJRTER)
Volume 02, Issue 02; February– 2016 [ISSN:2455-1457]

Working flow of proposed approach includes following steps:

1. Take RGB image
2. Image Color transformation of RGB to Gray scale
3. Image segmentation
4. Feature extractions
5. Statistical analyses
6. According to analysis matching of feature extraction are done.

4.1 Image Acquisition:

Disease detection start with taking input image from digital camera, those are in RGB format
[7] [1].
Better quality resolutions are used for image-analysis that images are in the format such as TIF,
JPEG, PNG, BMP etc.

RGB Gray scale

Fig. 4 RGB Images of infected sugarcane leaf

4.2 RGB to Gray scale Conversion:
In this method while converting the true color images RGB to gray scale by eliminating the hue and
saturation information [1].

4.3 Image pre-processing:

By using image pre-processing reject unwanted part of data from the image such as filter the noise,
image processing feature include the colour, size and texture of image.

4.4 Image Segmentation:

The result of input image segmentation for a plant disease detection system is to preserve only
the infected area in the output image for detection purpose [8]. However, due to the diversity of
disease types, the plants are growth in different environmental conditions. To predicate the final
result it may be hard to detect and problem of accuracy.
There is information need for prediction of disease is physical location of plant in environment and
its infected area of disease according to this information prediction is done [9].
Process for image segmentation based on color of image
1) Take Input image
2) Locate healthy area of image (which contains green pixels)
3) Extend to potentially infected area

@IJRTER-2016, All rights Reserved 29

 International Journal of Recent Trends in Engineering & Research (IJRTER)
Volume 02, Issue 02; February– 2016 [ISSN:2455-1457]
4) Get segmentation result.

IV. CONCLUSION
In this paper we have proposed feature extraction based concept of detecting disease of
sugarcane leaf. After doing review on various techniques and algorithms we had come to conclusion
that, SVM algorithm gives the better result as compare to other algorithms. This approach can also
be developed using normal techniques like JAVA, but using Matlab gives the efficient and effective
result. As the main focus of this application is user-friendly, this application id designed in such a
way that it supports Multi-Lingual concept. This application is helpful for farmer and laboratory
where they are can easily protect their crops and there will be increase in growth of production.

V. ACKNOWLEDGEMENT
I express my sincere gratitude towards my guide Prof. (Ms.) P.K Mitkal for her valuable
guidance. I also thank Prof. (Mr) Y.S.Lonkar [HOD] for their encouragement and support. Their
insight and comments will definitely lead to a better presentation for the ideas expressed in this
paper.

REFERENCES
[1] K. Padmavathi, Dr. K. Thangadurai, "Identification of Plant Leaves Disease Detection and Optimal Solution Using
Genetic Algorithm”, Berlin, Germany: Springer, 1989, vol. 61.
[2] Manoj Mukherjee, Titan Pal and Debabrata Samanta, “Damaged Paddy leaf detection using image processing",
Volume 3, No. 10, October 2012.
[3] K. Dang, H. Sun, J. P. Chanet, J. Garcia-Vidal, J. M. Barcelo-Ordinas, H.L. Shi and K.M. Hou, ”Wireless
Multimedia Sensor Network for plant disease detections", France-China International Workshop,18-20
Septembre2013, Clermont-Ferrand, France.
[4] H. Al-Hiary, S. Bani-Ahmad, M. Reyalat, M. Braik and Z. ALRahamneh, "Fast and Accurate Detection and
Classification of Plant Diseases", International Journal of Computer Applications (0975 – 8887) Volume 17– No.1,
March 2011.
[5] Sanjay B. Patil, “Leaf Disease Severity Measurement Using Image Processing”, International Journal of
Engineering and Technology Vol.3 (5), 2011, 297-301.
[6] P.Revathi, "Classification of Cotton Leaf Spot Diseases Using Image Processing Edge Detection Techniques",
Research Scholar, Computer Science Karpagam University Coimbatore - 21, Tamil Nadu, India, 2012 IEEE.
[7] Ravindra Nikam1, Mahesh Sadavarte, "Application of Image Processing Technique", National Conference on
Emerging Trends in Computer, Electrical & Electronics (ETCEE-2015) in Mango Leaves Disease Severity
Measurement.
[8] Burks TF, “Early detection of citrus diseases using machine vision”, Presentation at ASAE conference, Chicago,
USA, 2002.
[9] Renuka Rajendra Kajale, "Detection & Recognization of Plant leaf diseases using image processing and Andriod
OS", March-April, 2015.

@IJRTER-2016, All rights Reserved 30