Plant Leaf Disease Detection using Image Processing
Bukka Aswitha1, Ravikumar CV2, Venugopal P3

1Bukka Aswitha, Department of Electronics and Communication Engineering ,Vellore Institute of Technology, Vellore, India.
2Ravi kumar C.V , Assistant professor Sr. Department of Electronics and Communication Engineering ,Vellore Institute Of Technology, Vellore, India.
3Venugopal .P, Assistant professor Sr Department of Electronics and Communication Engineering, Vellore Institute of Technology, Vellore, India.
Manuscript received on April 20, 2020. | Revised Manuscript received on April 30, 2020. | Manuscript published on May 10, 2020. | PP: 409-414 | Volume-9 Issue-7, May 2020. | Retrieval Number: F4597049620/2020©BEIESP | DOI: 10.35940/ijitee.F4597.059720
Open Access | Ethics and Policies | Cite | Mendeley
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)

Abstract: Agriculture, the primary way to produce the food to the people besides its value added to the economy of the country’s gross domestic product. Plants are affected to various diseases and early detection of disease has to be done in order to reduce the social and economical loses. Nowadays farmers are not aware of the type of diseases that affect the plants and the respective measures that have to be taken in order to reduce the effect. This paper focuses on the technique that detects the disease using image processing techniques and providing the measures to the farmers to overcome the disease. The technique is based on the K means clustering which is used to segment the image after that the feature extraction is done based on the Gray level Coocurrence matrix approach then the Support Vector Machine classifier is used to classify the disease with the trained data. We have calculated the percentage of leaf affected and the measurement is done based on it. Here along with disease name its symptoms and measurement are shown. 
Keywords: Binary image, Gray level co occurrence matrix, K means clustering, support vector machine.
Scope of the Article: clustering