Plant Disease Analysis and Identification using Multi SVM Approach

Abstract

The identification and analysis of plant disease is beneficial for the farmers to prevent losses, and helps in increasing the quantity of agricultural product. The manual identification of plant disease requires a lot of time, which makes it difficult. Thus, automatic identification is essential. The proposed method presents an image processing based technique that helps in quickly recognizing the plant disease. This paper gives efficient and accurate plant disease detection and classification method using Multi SVM approach. It can detect three types of diseases Anthracnose, Bacterial Blight, black spot. The user can know the affected area of leaf in percentage by identifying the disease properly. The user can rectify the problem very easily and with less cost. Disease detection steps followed by the paper are pre-processing, segmentation, feature extraction and classification. In the image segmentation, proposed method use a K-means clustering algorithm to help in recognizing the defected area. The proposed method have used a Gray-Level co-occurrence matrix (GLCM) for obtaining the statistical measures from the matrix of a given image. In classification, the proposed method have used Multi-Class Support Vector Machine (MSVM), which extracts a feature vector from the text pair. The MSVM approach is quite flexible, since the feature vector may contain less, or different features, that helps in easily detecting the diseases.