Leaf Disease Detection Using KNN

Detection of plant diseases at starting stages is important for ensuring agricultural productivity and sustainability. In recent years, advancements in the field of Computer Vision and Machine Learning helped in the development of automated systems for plant disease detection using different leaf images. This research explores the use of deep learning techniques like KNN for the identification and classification of plant diseases into four categories Rust, Scab, Multiple Disease and Healthy, based on leaf images. The model also uses some preprocessing techniques like canny edge detection, ROI extraction, Histogram Equalization to make the data more refined. The model also invokes some methods like SMOTE and Transfer Learning for processing data more efficiently and making predictions more accurate.