Classification of Tomato Leaf Disease using Feature Extraction with KNN Classifier

Tomato cultivation plays a vital role in global agriculture, but the health of tomato plants is frequently compromised by various leaf diseases. Timely disease detection is crucial for effective management and prevention. In this paper, we propose a methodology for classifying tomato leaf diseases utilizing feature extraction and the k-nearest neighbors (KNN) classifier. We extract a combination of statistical and textural features, encompassing color, from tomato leaf images. Then these extracted features are fed into the KNN classifier, which categorizes leaves as healthy or diseased. The Plant Village dataset has been used for the evaluation of our methodology. A series of experimental results achieves an accuracy of 93.5%, demonstrating the effectiveness of the proposed methodology and thus providing a valuable tool for early disease identification in tomato crops.