Multi-resolution Collaborative Representation for Face Recognition

Sparse representation, collaborative representation, and other kinds of representation based classifiers have been extensively applied to face recognition. Specially, lots of experiments demonstrate that collaborative representation exhibits great potential. These existing classifiers generally focus on the single resolution. They do not work well for multiple resolution issues. However, images taken by different cameras in the real world have different resolutions. To deal with multi-resolution issues, this paper proposes a multi-resolution collaborative representation method. It builds multi-resolution training sample matrices and combines the collaborative representation to solve the multi-resolution recognition problem. Comparison experiments show that the proposed method exhibits the best comprehensive performance between all the tested methods.