Comparative Analysis of Random Forest, Support Vector Machine, and K-Nearest Neighbor with Image Feature Extraction for Rice Leaf Disease Detection

Nadia Nafista
Wawu Tri Ambodo
Analicia
Ulfa Siti Nuraini

Journal of Information Technology and Computer Science
Vol. 11 No. 2: August 2026

Plant diseases and pest infestations have caused a decline in global food production of up to 40%, including in Indonesia, making an efficient and accurate disease detection system essential to support food security. This study proposes a supervised learning approach to detect rice leaf diseases based on image processing. Leaf images are processed through the stages of image segmentation, normalization, Gaussian blur, Canny edge detection, visualization of diseased areas, and hybrid feature extraction. Supervised learning algorithms such as Random Forest (RF), Support Vector Machine (SVM), and K-Nearest Neighbor (KNN) were trained and compared. Test results show that Random Forest delivers the best performance with an accuracy of 97%, outperforming SVM and KNN. These findings indicate that the proposed approach can serve as an effective and reliable solution for the automatic detection of rice leaf diseases.