Low Resolution Face Recognition and Reconstruction Via Deep Canonical Correlation Analysis

Abstract

Low-resolution (LR) face identification is always a challenge in computer vision. In this paper, we propose a new LR face recognition and reconstruction method using deep canonical correlation analysis (DCCA). Unlike linear CCA-based methods, our proposed method can learn flexible nonlinear representations by passing LR and high-resolution (HR) image principal component features through multiple stacked layers of nonlinear transformation. As the nonlinear transformation in deep neural networks is implicit, we apply radial basis function based neural network to learn an explicit mapping between principal components and correlational features. In addition, we also design two residual compensation methods for identification and vision enhancement, respectively. The proposed approach is compared with existing LR face recognition and reconstruction algorithms. A number of experimental results on benchmark datasets have demonstrated the effectiveness and robustness of our method.