Joint coupled representation and homogeneous reconstruction for multi-resolution small sample face recognition

Xiaojin Fan, Mengmeng Liao, Jingfeng Xue, Hao Wu, Lei Jin, Jian Zhao, Liehuang Zhu

Abstract: Highlights•This paper proposes a novel multivariate dictionary learning framework.•A coherence enhancement term to improve the coherent representing of the coding coefficients under different resolutions.•A multivariate dictionary optimization method to solve dictionaries involving the calculation of fractional norm.•The proposed method achieves the state-of-the-art performance on several benchmark datasets.