Betel leaf classification using color-texture features and machine learning approach

Abstract

The existence of machine learning has been exploited to solve difficulties in various fields, including the classification of leaf species in agriculture. Betel leaf is one of the plants that provide health advantages. The objective of using a machine learning approach is to classify the betel leaf species. This study involved several processes: image acquisition, region of interest (ROI) detection, pre-processing, feature extraction, and classification. The feature extraction used the combination features of color and texture. Furthermore, the classification applied four classifiers, including artificial neural network (ANN), K-nearest neighbors (KNN), Naive Bayes, and support vector machine (SVM). The evaluation in this study implemented cross-validation with a K-fold value of 5. The method performance produced the highest accuracy value of 100% using the color and texture features with the SVM classifier.