Shared representation learning for heterogenous face recognition

After intensive research, heterogenous face recognition is still a challenging problem. The main difficulties are owing to the complex relationship between heterogenous face image spaces. The heterogeneity is always tightly coupled with other variations, which makes the relationship of heterogenous face images highly nonlinear. Many excellent methods have been proposed to model the nonlinear relationship, but they apt to overfit to the training set, due to limited samples. Inspired by the unsupervised algorithms in deep learning, this paper proposes a novel framework for heterogeneous face recognition. We first extract Gabor features at some localized facial points, and then use Restricted Boltzmann Machines (RBMs) to learn a shared representation locally to remove the heterogeneity around each facial point. Finally, the shared representations of local RBMs are connected together and processed by PCA. Near infrared (NIR) to visible (VIS) face recognition problem and two databases are selected to evaluate the performance of the proposed method. On CASIA HFB database, we obtain comparable results to state-of-the-art methods. On a more difficult database, CASIA NIR-VIS 2.0, we outperform other methods significantly.