CLASSIFICATION OF LEAF DISEASES IN APPLE USING SUPPORT VECTOR MACHINE

Abstract

India is an agricultural country, and 70% of the population depends on agriculture, hence heavy crop losses due to plant diseases results in loss of several billion dollars annually. This paper mainly concentrates on detection of leaf diseases. In rural areas and in developed countries, the naked eye observation of agricultural experts to detect the plant diseases is cumbersome. It takes too much of cost and time. This paper aims to provide a fast and cheap solution through automatic detection of leaf diseases and thus to improve the yield of the crops by detecting the plant diseases at the earlier stage. Using image processing, we can able to identify the type of disease in plant leaf by analyzing the color and texture feature. In our system first, color transformation is done from RGB to HSV and followed by color feature extraction. In color feature analysis, the color distribution of pixels is represented by the mean and standard deviation of the image and the local color information is represented by a binary bitmap. For texture feature extraction, first green pixels are masked as they are healthy region. This is followed by segmentation using K means clustering and identification of significant segments. From the selected segments, the Gray level co-occurrence matrix (GLCM) is found. From GLCM, the texture features are extorted. Using SVM diseased plant is discriminated from the healthy plant and classified based on diseases. Classification accuracy is measured through the performance measures such as precision and recall.