Image classification by non-negative sparse coding, correlation constrained low-rank and sparse decomposition

• We use non-negative sparse coding with max pooling to represent images.
• Use correlation constrained low-rank matrix recovery to decompose image features.
• Locality-constrained linear coding is used to recode image representation.
• We achieve the state-of-the-art performances on several public datasets.

We propose an image classification framework by leveraging the non-negative sparse coding, correlation constrained low rank and sparse matrix decomposition technique (CCLR-Sc+SPM). First, we propose a new non-negative sparse coding along with max pooling and spatial pyramid matching method (Sc+SPM) to extract local feature’s information in order to represent images, where non-negative sparse coding is used to encode local features. Max pooling along with spatial pyramid matching (SPM) is then utilized to get the feature vectors to represent images. Second, we propose to leverage the correlation constrained low-rank and sparse matrix recovery technique to decompose the feature vectors of images into a low-rank matrix and a sparse error matrix by considering the correlations between images. To incorporate the common and specific attributes into the image representation, we still adopt the idea of sparse coding to recode the Sc+SPM representation of each image. In particular, we collect the columns of the both matrixes as the bases and use the coding parameters as the updated image representation by learning them through the locality-constrained linear coding (LLC). Finally, linear SVM classifier is trained for final classification. Experimental results show that the proposed method achieves or outperforms the state-of-the-art results on several benchmarks.