Plant Leaf Disease Detection using Machine Learning

Abstract

Plant leaf disease detection is a critical task in modern agriculture to ensure better crop yield and quality. This provides a unique strategy for detecting plant leaf disease using machine learning techniques. The proposed methodology consists of three main stages, followed by classification using five different models, including KNN, SVM, Decision Trees, Random Forest, and CNN. The collected images are pre-processed to eliminate unwanted features, and the images are resized to a standardized size of $256\times 256$ pixels. The following stage involves utilizing the pre-trained CNN model to extract pertinent features. The extracted features are then utilized to train the classification models. The performance of each model is assessed using various metrics, to predict its effectivity and accuracy. This proposed methodology is expected to provide a reliable and efficient diagnosis of plant diseases, helping farmers to take timely measures to prevent disease outbreaks and ensure healthy crop growth. The proposed system achieved high accuracy, less complexity, and easy identification. The experimental findings show that the suggested paradigm is successful in identifying common diseases. The suggested method of early detection and diagnosis of crop diseases can result in timely treatment and higher crop yield.