Plant disease detection using image processing and machine learning

Abstract

In agriculture plant disease and its precise detection is an important task and researchers have attempted lots of methods to automate the task of disease detection using latest tools and techniques of image processing and machine learning. This work is designed to the semi-automatic system to detect two diseases of soybean (Glycine max) named mosaic virus and Leaf spot applied method of doing k-means clustering extracting the combined colour and texture features from the diseased area of soybean leaves and classified using KNN algorithm. It is reported that it gives better accuracy comparing with existing work. Visual observation of leaf sample also proves the suitability of the proposed system for detection and classification.