Robust pattern for face recognition using combined Weber and pentagonal-triangle graph structure pattern

Face recognition is a challenging task in computer vision and information retrieval due to the large variation in facial images in terms of pose, expression and illumination. These challenges motivate us to propose a robust pattern for face recognition using combined Weber pattern (CWP) and pentagonal-triangle graph structure pattern (PTGSP). Firstly, abrupt intensity variations in facial images are removed by multiblock operation. Further, by exploring the relationship among center, neighboring and adjacent pixels, CWP consisting of three unique Weber patterns is computed. In order to obtain the pattern that is more robust to facial variations, PTGSP has been computed on the facial images. PTGSP covers the widely used features of face images. A feature set of high dimension is produced by combining the features of CWP and PTGSP. Dimensionality of the proposed feature and also variance within class is reduced through principal component analysis (PCA) plus linear discriminant analysis (LDA) algorithm. The classification performance of the proposed method is compared with various state-of-the-art methods on variety of benchmark face datasets with variation in pose, expression, illumination and occlusion. Experiments on FEI, Georgia, ORL, Yale and Faces94 databases clearly prove the robustness of the proposed method in contrast to existing handcrafted feature extraction techniques.