<![CDATA[Manual identification of herbal leaves often leads to errors due to visual similarities between species, variations in lighting, and morphological differences that are difficult to observe consistently. These conditions make the identification process subjective, inefficient, and less accurate, so a more reliable automated approach is needed. This study aims to evaluate and compare the performance of the Support Vector Machine (SVM) and K-Nearest Neighbor (K-NN) algorithms in classifying five types of herbal leaves using a combination of shape, color, and texture features. The dataset consists of 1,000 herbal leaf images obtained from various sources and processed through preprocessing, feature extraction of shape (metric, eccentricity), color (HSV), and texture (GLCM). The data were then normalized, divided by a ratio of 80:20, and optimized using hyperparameter tuning. Evaluation was carried out using accuracy, precision, recall, and F1-score metrics. The test results showed that SVM achieved the highest accuracy of 94.48%, outperforming K-NN which achieved an accuracy of 92.18%. SVM also showed more stable performance in handling complex feature combinations. This research contributes by presenting an effective shape–color–texture feature-based integrative classification framework for herbal leaf identification, as well as strengthening the application of machine learning in the development of plant identification systems in the field of informatics, both for desktop, web, and mobile applications.]]>
