Leaf Disease Classification Using Machine Learning Techniques

Abstract

Machine learning techniques are widely used in many fields, in this paper machine learning classification algorithms are used in an aquaponic system for plant disease classification. Aquaponics is an efficient and smart method of growing crops in water. In an aquaponic system, freshwater fishes known to benefit leafy crops the most. But the plants get affected due to certain disease in the leaves. In this paper, four different supervised machine learning algorithms are used to detect and classify the tomato leaf diseases. The process involved in the classification of the tomato leaf disease are leaf Image acquisition, Image preprocessing, augmentation, feature extraction and classification.The classifier algorithms used for classifying the leaf disease are Support Vector Machine (SVM), Knearest neighbour(KNN), random forest and decision trees. Feature extraction is done with vgg16 convolution neural network architecture. By applying the four classification algorithm over the features extracted images, Support Vector Machine (SVM) performed well among the four classification algorithms by classifying the tomato leaf diseases with an accuracy of 99%.