Locally nonlinear regression based on kernel for pose-invariant face recognition

The variation of facial appearance due to the viewpoint or pose obviously degrades the accuracy of any face recognition systems. One solution is generating the virtual frontal view from any given non-frontal view. In this paper, we propose an efficient and novel locally kernel-based nonlinear regression (LKNR) method, which generates the virtual frontal view from a given non-frontal face image. Eventually, after non-frontal face images are converted to virtual frontal view, we use PCA+FLDA method for pose-invariant face recognition. The comparison of the proposed method with locally linear regression (LLR) and eigen light-field (ELF) methods show that the proposed method outperforms two other methods in terms of robustness, visual effects and recognition accuracy.