Plant Leaf Disease Recognition Using Machine Learning

Abstract— Plant leaf diseases significantly impact agricultural productivity, leading to substantial crop losses if not detected early. This paper introduces a deep learning approach for automatically identifying and classifying potato leaf diseases using image data. By utilizing transfer learning with MobileNetV2, a lightweight yet efficient CNN, the system accurately distinguishes between Early Blight, Late Blight, and Healthy leaves. The process includes dataset collection, preprocessing, model training, and real-time web application deployment for user interaction. Experimental results highlight high prediction accuracy and practical feasibility, making this system a valuable asset for precision agriculture and crop protection. Keywords— Plant leaf Disease Detection, Convolutional Neural Networks (CNNs), Image Classification, Transfer Learning, MobileNetV2, Image Preprocessing, Crop Protection, Deep Learning.