Performance Analysis of AI-based Learning Models on Leaf Disease Prediction

Diseases on the leaves of a plant have a great effect on agriculture. Around 70-75% of the Indians are totally dependent on agriculture. Diseases on plant leaves reduce the yield and quantity of the product. In this paper, the different analysis of methods are used to detect plant leaf diseases using various machine learning (ML) algorithms such as Support Vector Machine (SVM), K-Nearest Neighbor (KNN), Naive-Bayes, Logistic Regression, Artificial Neural Network (ANN), Convolutional Neural Network (CNN), Back propagation, Genetic algorithm and Probabilistic Neural Network (PNN) was done. The SVM algorithm which is used to detect tomato plant leaf diseases gives 96% prediction whereas the Back Propagation algorithm which is used to detect groundnut leaf diseases obtained 97.41% prediction. Our work focuses on the analysis of various leaf disease detection techniques and also provides an overview of various image processing techniques. The main purpose of the paper is to support the identification of plant affected by various diseases. A comparative analysis of various leaf disease detection has been done in this paper.