Hybrid System for Detection and Classification of Plant Disease Using Qualitative Texture Features Analysis
The various bacterial/fungal capsicum diseases are discussed, how to identify/classify these diseases using image processing technique and how these diseases can be classified by using support vector machine (SVM).
Abstract
Diseases in plants causes' major production as well as economic losses, to enhance crop production it is most important that plant diseases must be analyzed earlier so that effective control actions can be taken. This paper discusses the various bacterial/fungal capsicum diseases, how to identify/classify these diseases using image processing technique, capsicum is exposed to be infected by various bacterial, fungal and virus diseases, these disease symptoms are distinguishable through inspecting either stem, leave or fruit part of the capsicum.This proposed algorithm/method automatically identifies the capsicum diseases and classifies whether the capsicum or its leaf is normal or diseased i.e. having either bacterial or fungal disease, the infected area of the capsicum is extracted out by k-means clustering technique after that texture i.e. GLCM features are extracted for this infected area, by these features various bacterial/fungal capsicum diseases can be classified by using support vector machine (SVM). The different classifiers like Tree, Linear Discriminant, KNN and SVM are used for training and classification purpose, out of these classifiers KNN and SVM gives better results for our application. This system is tested on 62 images of healthy/diseased capsicum and its leaves, by SVM these images are well classified into healthy and diseased one with accuracy of 100%.