Patterns of weber magnitude and orientation for face recognition

Feature extraction is vital for a successful face recognition system. In this paper, we propose a computationally efficient, discriminative and robust feature descriptor for face images, named Patterns of Weber magnitude and orientation (PWMO), which encodes Weber magnitude and orientation with patch-based local binary pattern (p-LBP) and patch-based local XOR pattern (p-LXP), respectively. Furthermore, whitened PCA is introduced to reduce the feature dimensionality and select the most discriminative feature sets, and the block-based scheme is incorporated to address the small sample size problem. The effectiveness and robustness of our proposed approach has been demonstrated experimentally on the well-known FERET database.