Combining sparse representation and singular value decomposition for plant recognition

Abstract

Plant recognition is one of important research areas of pattern recognition. As plant leaves are extremely irregular, complex and diverse, many existing plant classification and recognition methods cannot meet the requirements of the automatic plant recognition system. A plant recognition approach is proposed by combining singular value decomposition (SVD) and sparse representation (SR) in this paper. The difference from the traditional plant classification methods is that, instead of establishing a classification model by extracting the classification features, the proposed method directly reduces the image dimensionality and recognizes the test samples based on the sparse coefficients, and uses the class-specific dictionary learning for sparse modeling to reduce the recognition time. The proposed method is verified on two plant leaf datasets and is compared with other four existing plant recognition methods The overall recognition accuracy of the proposed approach for the 6 kinds of plant leaves is over 96%, which is the best classification rate. The experimental results show the feasibility and effectiveness of the proposed method.