Texture based Leaf Disease classification using Machine Learning Techniques

Abstract

Machine learning techniques has emerged as a potential field in many of present day agricultural applications. One of these applications is the identification and classification of leaf diseases. In this paper, a triangular based and OTSU based methods are applied for segmentation, Textural features primarily based on GLCM are obtained for these segmented images using k-means clustering technique, further classification of different leaf disease is performed using an SVM based classification. The proposed method resulted in an overall classification accuracy of 70% using the triangular based segmentation with an AUC of 0.63.