Discriminative dictionary learning via Fisher discrimination K-SVD algorithm

Abstract

Listen

Translate article

An efficient and discriminative dictionary structure is important for pattern classification. Considering the discrimination of the sparse coding coefficients, a method named Fisher Discriminative K-SVD (FD-KSVD) is proposed to learn an over-complete discriminative dictionary and an optimal linear classifier. In FD-KSVD, the Fisher discrimination criterion is imposed on the sparse coding coefficients to make them discriminative through small within-class scatter and big between-class scatter. Hence not only the reconstruction error can be used, but also the discriminative error and the classification error have been represented. The optimization is employed by the Iterative Projective Method and K-SVD method alternatively. Experimental results demonstrate that our proposed method outperforms many other state-of-the art methods for face and palmprint recognition.