An Automated System for Detection and Classification of Rice Plant Diseases

This paper describes the automation of the identification of rice plant diseases using multi SVM algorithm. Productivity of rice decreases due to infections caused by various types of diseases in its leaf and stem. Leaf diseases are caused by bacteria, fungi, virus etc. Diseases are a major factor limiting crop production and diseases are often difficult to control. Without accurate disease identification, proper control methods cannot be used at time. Image processing is popularly used technique to identify the plant diseases detection and classification. Initially the diseased region is found using K-means clustering, then both color and texture features are extracted. Finally classification technique is used to detect the type of rice disease. A web server is connected to the system so that individual can upload the infected plant image and identify the disease. The proposed system can successfully detect and classify the examined diseases with over 84.41% accuracy.