3D Face Recognition system Based on Texture Gabor Features using PCA and Support Vector Machine as a Classifier

Pioneer 2D face recognition based on intensity or color images encounters many challenges, like variation in illumination, expression, and pose variation. In fact, the human face generates not only 2D texture information but also 3D shape information. In this paper, the main objective is to analyze what contributions depth and intensity with texture information make to the solution of face recognition problem when expression and pose variations are taken into account, and a new proposed system is introduced for combining depth, texture and intensity information in order to improve face recognition performance. In the proposed approach, local features based on Gabor wavelets are extracted from depth, texture and intensity images, which are obtained from 3D data after fine alignment. Then a novel hierarchical selecting scheme embedded in symbolic principal component analysis (Symbolic PCA). Then a Support vector classifier is used for classification of the extracted features. All the Experiments are performed on the Bhosphorus 3D face database, which contain images of faces with various complex variations, including expressions, poses and long time lapses between two scans. The experimental result demonstrates the effectiveness in the performance of the proposed method.