Competitive Non-negative Representation with Image Gradient Orientations for Face Recognition

Non-negative representation based classification (NRC) has achieved encouraging results in various pattern classification applications. Unfortunately, it still has some deficiencies. First, regularization term is absent in the objective function of NRC, which may produce an unstable solution and lead to misclassification. Second, NRC is not robust to occluded training samples. To address the above two problems, we propose a competitive NRC with image gradient orientations (IGO-CNRC) for face recognition. Concretely, first we introduce a competitive regularization term into the formulation of NRC and thereby present a competitive NRC (CNRC) method. To further increase the robustness to occluded training samples, we extract multiple-order image gradient orientations (IGOs) of samples and obtain the residuals under the framework of CNRC. Then these residuals are fused by the sum rule and the test sample is classified into the class that yields the least residual. Experimental results on standard face databases document the effectiveness of IGO-CNRC. The MATLAB code of IGO-CNRC is available at https://​github.​com/​yinhefeng/​IGO-CNRC