Classification of Diseased Potato Leaves Using Machine Learning
Sakshi Sharma, Vatsala Anand, Swati Singh
Abstract
Plant disease detection offers a favorable step towards sustainable agriculture and disinfected crops. Early detection of disease in plants i.e., disease control and management lead to improvement in the quality of crops as well as reduce the production losses. This work presents an approach that integrates image processing and machine learning for disease diagnosis by utilizing potato leaf images. In this work, two potato leaf diseases; early blight and late blight are classified using various machine learning algorithms such as Support Vector Machine (SVM), K-Nearest Neighbor (KNN), Naïve Bayes and Decision Tree. The diseased leaf images are filtered using Gaussian filter and then, the desired Region of Interest (ROI) is obtained using K means clustering algorithm. Different machine learning classifiers are used to classify the two potato leaf disease, out of which support vector machine gives the best accuracy of 92.9%.