Similarity preserving analysis based on sparse representation for image feature extraction and classification

Sparse representation has been a very active research area in recent years. Similarity analysis is an attractive research topic in the field of pattern recognition. In this paper, we take advantage of sparse representation in similarity analysis, and propose a novel unsupervised feature extraction approach, named similarity preserving analysis based on sparse representation (SPASR). SPASR projects samples from a high-dimensional space into a low-dimensional subspace, where the sparse reconstructive similarity relations among samples and the similarities of original samples and sparsely reconstructed samples are preserved. Experiments on the AR face database and COIL-20 object database demonstrate that the proposed SPASR approach outperforms several representative unsupervised subspace learning methods.