Automated classification of Wuyi rock tealeaves based on support vector machine

This paper describes a new automated classification method for Wuyi rock tealeaves based on the best penalty parameter selection for the support vector machine with RBF (Radial Basis Function) kernel. A total of 3590 fresh tealeaf images of the representative Rou Gui and Shui Hsien varieties of Wuyi rock tea are collected in their natural habitat. Fourteen image features are extracted in terms of the leaf shape and texture. The automatic selection method is used to find the optimum RBF kernel parameter sigma, which is then applied to design an automatic parameter selection method to screen the best penalty parameter C for the classification of Wuyi rock tealeaves. In this study, the SVM classifier is used for the automated classification and recognition of the 14 image features. The contribution of the various features to the recognition rate of fresh tealeaves is evaluated to identify the key features for the classification and recognition of fresh Wuyi rock tealeaf images. The experimental results show that the proposed method improves the recognition rate of fresh tealeaves to 91.00%.