Face Recognition Using the Combination of Weighted Sparse Representation-based Classification and Singular Value Decomposition Face

Abstract

Given the increasing need for the creation and development of automated systems, the problem of detecting and identifying the faces of people in the images has been considered by the researchers. In recent years, the sparse representation based classification has been of great interest to researchers. The goal of this investigation is to provide a quick and effective way to identify faces based on the sparse representation. Since the basis of sparse representation is to calculate it through L1-norm optimization for high dimensional dictionary with high computational volume, a smoothed L0-norm optimization-based method was introduced. At the time of obtaining the sparse representation using smoothed L0-norm, due to the high degree of redundancy, when the number of facial features is low, the conditions for the unique sparse representation are not properly satisfied or the model is not accurate, the risk of getting stuck in the local minima will be so much. Hence, the idea of the weighted sparse representation to narrow the search space is presented. In addition, to enhance the identification accuracy in face recognition and face verification under varying illumination conditions, the Singular Value Decomposition method can be used in the feature extraction step. In the extraction stage, the normalized coefficients of Singular Value Decomposition are not sensitive to different lightness conditions, resulting to reduce the effect of illumination variation on the normalized images. Compared to earlier methods, which often fail even in the event of a slight turbulence, this technique can successfully produce facial structural information while preventing the effect of different lightnesses such as cast shadows. The simulation results on the Extended Yale B database show that the proposed method has high accuracy in face recognition with less computational volume and higher speed than the L1-norm based approach.