Potato plants, valued globally for their nutritional and economic importance, are highly vulnerable to various diseases, making early and accurate detection crucial to reducing yield loss and economic impact. This work presents a novel approach that integrates Fuzzy C-Means (FCM) clustering-based segmentation with convolutional neural network (CNN) models for the classification of potato leaf diseases. The method begins by segmenting leaf images in the Lab color space, chosen for its perceptual uniformity and its enhanced ability to separate color and luminance compared to the conventional RGB space. FCM, a soft clustering technique, allows each pixel to belong to multiple clusters with varying degrees of membership, effectively capturing ambiguous boundaries between healthy and diseased regions. By segmenting the images prior to classification, the influence of background noise on disease identification is significantly reduced. Experimental results demonstrate that the FCM-based segmentation approach achieves a test accuracy of approximately 94%, outperforming the baseline (no segmentation), which achieves around 91%. Additionally, FCM surpasses traditional clustering methods such as K-means, providing an accuracy improvement of over 2%. The integration of Lab color space segmentation, FCM clustering, and CNN classification forms a robust framework that significantly improves the accuracy and timeliness of potato disease detection, supporting sustainable crop management.
Full publication URL
