An Improved Leaf Disease Detection Method using Clustering Optimization and Multi-Class Classifier Technique

Abstract

Agriculture is the only passion to cultivate foods, raising a human’s life and animals by producing desired plant products. India ranked in the world's five largest producers of over 80% of agricultural produce items, including many cash crops such as rice, guava, tobacco, etc. Identification of the plant diseases is the key to preventing the losses in the yield and quantity of the agricultural product. Health monitoring and disease detection on plant is very critical for sustainable agriculture. It is very complicated to monitor the plant diseases manually because it requires marvelous amount of work, skilled person in the plant diseases and also need the excessive processing time. The identification of objects in an image is probably start with image processing techniques such as noise removal, followed by (low-level) feature extraction to locate lines, regions and possibly areas with certain textures. Consequently, image processing is used for the detection of plant diseases. The proposed system consist of following phases like: image preprocessing, image segmentation using OTSU segmentation, clustering of an image using K-means, feature extraction using GLCM feature extraction, classification of the image by Multi class SVM classifier. In compared to existing system, the proposed system significantly identifies the plant leaf disease at an early disease and with an accuracy 96.7%.