A New Segmentation method for Plant Disease Diagnosis

Abstract

Detecting plant diseases automatically with the help of symptoms present on leaves at earlier stage yields more productivity in agriculture. In this paper, a novel plant disease diagnosis method is proposed for the plants using image processing techniques and SVM classifier. Here, disease diagnosis is carried based on features extracted from the segmented image after pre-processing the image of the leaves which are affected with diseases. Modified color processing detection algorithm (CPDA) is used as segmentation method to extract the features. SVM classifier is trained with a dataset of about 100 images of diseased leaves to identify the diseases like anthracnose, leafspot, leafblight, scab. For disease detection, the performance of proposed segmentation technique is better when compared to the K-means clustering segmentation.