Sparse Representation-based Classifier (SRC) is less sensitive to the shortage of data and the selection of feature space. In this paper, SRC is adopted to perform automatic analysis of tongue substance color and coating color which is considered as small dataset classification task. Firstly, for both training samples and testing samples, the tongue body regions are segmented, the regions of tongue substance and coating are separated and the features of these regions are extracted. Then, the feature vectors of testing samples are represented by sparse coding. Finally, the feature vectors of testing samples are reconstructed for each category, the residuals are calculated and the category of the smallest residual is determined as the classification result. Experimental results show that the proposed method can achieve the classification accuracy of 87.80% and 90.51% for the colors of tongue substance and tongue coating respectively. In addition, the classification accuracy of tongue coating color can reach to 91.19% with the assistance of visual samples by SRC. The proposed method provides a new method for automatic analysis of tongue color, and it is also a new application of SRC.
