Vector quantization with constrained likelihood for face recognition

In this paper, we investigate the problem of visual information encoding and decoding for face recognition. We propose a decomposition representation with vector quantization and constrained likelihood projection. The optimal solution is considered from the point of view of the best achievable classification accuracy by minimizing the probability of error under a given class of distortions. The performance of the proposed model of information encoding/decoding is compared with the performance of those based on sparse representation. The computer simulation results confirm the superiority of the proposed vector quantization based recognition over sparse representation based recognition on several face image databases.