See discussions, stats, and author profiles for this publication at: https://www.researchgate.

net/publication/318109025

Leaf Disease Detection using Image Processing

Article in Journal of Chemical and Pharmaceutical Sciences · March 2017

CITATIONS READS

66 52,784

1 author:

Suja Radha
VIT University
99 PUBLICATIONS 1,485 CITATIONS

SEE PROFILE

Some of the authors of this publication are also working on these related projects:

Classification & Prediction View project

Edited Book View project

All content following this page was uploaded by Suja Radha on 23 November 2017.

The user has requested enhancement of the downloaded file.

 ISSN: 0974-2115
www.jchps.com Journal of Chemical and Pharmaceutical Sciences
Leaf disease detection using image processing
Sujatha R*, Y Sravan Kumar and Garine Uma Akhil
School of Information Technology and Engineering, VIT University, Vellore
*Corresponding author: E-Mail: [email protected],
ABSTRACT
Identification of plant disease is very difficult in agriculture field. If identification is incorrect then there is
a huge loss on the production of crop and economical value of market. Leaf disease detection requires huge amount
of work, knowledge in the plant diseases, and also require the more processing time. So we can use image processing
for identification of leaf disease in MATLAB. Identification of disease follows the steps like loading the image,
contrast enhancement, converting RGB to HSI, extracting of features and SVM.
KEY WORDS: Contrast enhancement, HSI, SVM, RGB.
1. INTRODUCTION
India is fast developing country and agriculture is the back bone for the countries development in the early
stages. Due to industrialization and globalization concepts the field is facing hurdles. On top of that the awareness
and the necessity of the cultivation need to be instilled in the minds of the younger generation. Now a day’s
technology plays vital role in all the fields but till today we are using some old methodologies in agriculture.
Identifying plant disease wrongly leads to huge loss of yield, time, money and quality of product. Identifying the
condition of plant plays an important role for successful cultivation. In olden days identification is done manually
by the experienced people but due to the so many environmental changes the prediction is becoming tough. So we
can use image processing techniques for identification of plant disease. Generally we can observe the symptoms of
disease on leafs, stems, flowers etc. so here we use leafs for identification of disease affected plants.
Literature Survey: The feature extraction is done in RGB, HSV, YIQ and Dithered Images. The feature extraction
from RGB image is added in the suggested system. A new automatic method for disease symptom segmentation in
digital photographs of plant leaves. The diseases of different plant species has mentioned. Classification is done for
few of the disease names in this system. The disease recognition for the leaf image is performed in this work.
Study and analysis of cotton leaf disease detection using image processing work is carried on. The k means
Clustering algorithm is used for segmentation. The k-means concept is added to the proposed system which will
divide the leaf into different clusters. The survey of disease identification on cotton leaf is done. Comparison of
different detection technique of leaf disease detection is mentioned. SVM and k-means clustering has used in this
system.
An identification of variety of leaf diseases using various data mining techniques is the potential research
area. The diseases of different plant species has mentioned. Classification is done for few of the disease names in
this system. The concept SVM for classification is used in this system.
Proposed Methodology:

Figure.1. Flow chat for disease detection

Image Acquisition: First we need to select the plant which is affected by the disease and then collect the leaf of the
plant and take a snapshot of leaf and load the leaf image into the system.
Segmentation: It means representation of the image in more meaningful and easy to analyse way. In segmentation
a digital image is partitioned into multiple segments can defined as super-pixels.

Figure.2. Enhanced Image

Low Contrast: image pixel values are concentrated near a narrow range.
Contrast Enhancement: In figure.2, the original image is the image given to the system and the output of the system
after contrast enhancement is Enhanced Image, this is the image after removing the sharp edges.

January - March 2017 670 JCPS Volume 10 Issue 1

 ISSN: 0974-2115
www.jchps.com Journal of Chemical and Pharmaceutical Sciences

Figure.3. Pixel range

Converting RGB to HSI: The RGB image is in the size of M-by-N-by-3,where the three dimensions account for
three image planes(red, green, blue).if all the three components are equal then conversion is undefined.
Generally the pixel range of RGB is [0,255] in his the pixel range is [0, 1].Conversion of pixel range can be
done by calculating of the components; Hue, Saturation, Intensity.
HUE:
𝑛𝑢𝑚𝑒𝑟𝑎𝑡𝑜𝑟 = 1/2[(𝑅 − 𝐺) + (𝑅 + 𝐵)]
𝑑𝑒𝑛𝑜𝑚𝑖𝑛𝑎𝑡𝑜𝑟 = ((𝑅 − 𝐺)2 + ((𝑅 − 𝐵) ∗ (𝐺 − 𝐵)))^0.5
Now find theta value for
ℎ = 𝑎𝑐𝑜𝑠𝑑(𝑛𝑢𝑚𝑒𝑟𝑎𝑡𝑜𝑟/𝑑𝑒𝑛𝑜𝑚𝑖𝑛𝑎𝑡𝑜𝑟)
Saturation:
3
𝑠 =1−( ) ∗ min⁡[𝑅, 𝐺, 𝐵]
𝑅+𝐺+𝐵
Intensity
(𝑅 + 𝐺 + 𝐵)
𝐼=
3
Then combine the three results into one single value then the HIS image is formed.

Figure.4. HSI image

k-means clustering algorithm: This algorithm is used to cluster/divide the object based on the feature of the leaf in
to k number of groups. This is done by using the Euclidean distance metric.
The algorithm of k means
 Initialization: User should select the value of k. k means the number of clusters/groups, i.e. the image is
divided in to k number of clusters.
 Every pixel is assigned to its nearest centroid (k).
 The position of centroid is changed by means of data values assigned to the group. The centroid moves to
the centre of its assigned points.
Out of these three clusters classification is done for only one cluster which has affected area.

Figure.5. Clustered image

Support Vector Machine (SVM): SVM is a statistical learning-based solver. Statistical is a mathematics of
uncertainty.it aims at gaining knowledge, making decisions from a set of data.

January - March 2017 671 JCPS Volume 10 Issue 1

 ISSN: 0974-2115
www.jchps.com Journal of Chemical and Pharmaceutical Sciences

Figure.6. SVM
In the above figure a simple classification problem is given in two dimensional input space. The two types
of pattern indicate the images of crescent-shaped and oval objects. We can draw a line separating the two classes and
many such possibilities exist. It is clear that figure (b) is better classified than figure (a) because there is less error.
Figure (c) may be the optimal line of separation. A line becomes a plane if we have three attributes variables instead
of two, and becomes a hyperplane if there are more than three attributes. Figure (c) represents what is known as the
optimal hyper plane (OH). Another name of OH is maximal margin hyperplane.

Figure.7. Disease name Figure.8. Output

2. CONCLUSION
This study summarizes major image processing used for identification of leaf diseases are k-means
clustering, SVM. This approach can significantly support an accurate detection of leaf disease. There are five steps
for the leaf disease identification which are said to be image acquisition, image pre-processing, segmentation, feature
extraction, classification. By computing amount of disease present in the leaf, we can use sufficient amount of
pesticides to effectively control the pests in turn the crop yield will be increased. We can extend this approach by
using different algorithms for segmentation, classification.
By using this concept the disease identification is done for all kinds of leafs and also the user can know the
affected area of leaf in percentage by identifying the disease properly the user can rectify the problem very easy and
with less cost.
REFERENCES
Barbedo, Jayme Garcia Arnal, A new automatic method for disease symptom segmentation in digital photographs
of plant leaves, European Journal of Plant Pathology, 2016, 1-16.
Bhong, Vijay S and Pawar B.V, Study and Analysis of Cotton Leaf Disease Detection Using Image Processing,
International Journal of Advanced Research in Science, Engineering and Technology, 3 (2), 2016.
Lumb, Manisha, and Poonam Sethi, Texture Feature Extraction of RGB, HSV, YIQ and Dithered Images using
GLCM, Wavelet Decomposition Techniques, International Journal of Computer Applications, 68 (11), 2013.
Reena Tijare, Pawan Khade, Rashmi Jain, The Survey of Disease Identification of Cotton Leaf, International Journal
of Innovative Research in Computer and Communication Engineering, 2015.
Sasirekha N, Swetha N, An Identification of Variety of Leaf Diseases Using Various Data Mining Techniques,
International Journal of Advanced Research in Computer and Communication Engineering, 4 (10), 2015.
Zhang S. W, Shang Y.J, and Wang L, Plant Disease Recognition Based on Plant Leaf Image, Journal of Animal and
Plant Sciences, 25 (1), 2015, 42-45.

January - March 2017 672 JCPS Volume 10 Issue 1

View publication stats