Authors: Chao Zhang, Huaxiong Li, Chunlin Chen, Yuhua Qian, Xianzhong Zhou

Abstract:

Regression analysis based methods have shown strong robustness and achieved great success in face recognition. In these methods, convex l1-norm and nuclear norm are usually utilized to approximate the l0-norm and rank function. However, such convex relaxations may introduce a bias and lead to a suboptimal solution. In this paper, we propose a novel Enhanced Group Sparse regularized Nonconvex Regression (EGSNR) method for robust face recognition. An upper bounded nonconvex function is introduced to replace l1-norm for sparsity, which alleviates the bias problem and adverse effects caused by outliers. To capture the characteristics of complex errors, we propose a mixed model by combining γ- norm and matrix γ-norm induced from the nonconvex function. Furthermore, an l2;γ-norm based regularizer is designed to directly seek the interclass sparsity or group sparsity instead of traditional l2;1-norm. The locality of data, i.e., the distance between the query sample and multi-subspaces, is also taken into consideration. This enhanced group sparse regularizer enables EGSNR to learn more discriminative representation coefficients. Comprehensive experiments on several popular face datasets demonstrate that the proposed EGSNR outperforms the state-of-the-art regression based methods in robust face recognition.

Keywords： Face Recognition, Robustness, Training, Nuclear Magnetic Resonance, Sparse Matrices, Encoding, Periodic Structures, Low Rank Structure, Sparse Representation, Enhanced Group Sparsity, Nonconvex Relaxation,

Enhanced Group Sparse Regularized Nonconvex__Regression for Face Recognition.pdf

查看详情

Tue May 11 18:57:27 CST 2021