Three Dimensional Face Recognition Using SVM Classifier

In this paper, we presented a novel approach for automated 3D face recognition using range data. An object recognition system generally consists of two main parts: data registration and data comparison. In first step, the nose tip was used as the reference point and 3D face shape was normalized to standard image size. The 2DPCA was applied to the resultant range data and the corresponding principal images were used as the feature vectors. Classification was carried out by calculating the similarity score between the feature vectors. The SVM classifier was used in choosing the closest match. Recognition rate of 97% rank-four was achieved.

[1]  Vladimir N. Vapnik,et al.  The Nature of Statistical Learning Theory , 2000, Statistics for Engineering and Information Science.

[2]  Hiromi T. Tanaka,et al.  Curvature-based face surface recognition using spherical correlation. Principal directions for curved object recognition , 1998, Proceedings Third IEEE International Conference on Automatic Face and Gesture Recognition.

[3]  Christopher J. C. Burges,et al.  A Tutorial on Support Vector Machines for Pattern Recognition , 1998, Data Mining and Knowledge Discovery.

[4]  Gaile G. Gordon,et al.  Face recognition based on depth maps and surface curvature , 1991, Optics & Photonics.

[5]  J. Vélez,et al.  Face recognition using 3D local geometrical features: PCA vs. SVM , 2005, ISPA 2005. Proceedings of the 4th International Symposium on Image and Signal Processing and Analysis, 2005..

[6]  Ross T. Whitaker,et al.  Geometric surface smoothing via anisotropic diffusion of normals , 2002, IEEE Visualization, 2002. VIS 2002..

[7]  J. Cartoux,et al.  Face authentification or recognition by profile extraction from range images , 1989, [1989] Proceedings. Workshop on Interpretation of 3D Scenes.

[8]  Stefanie Eberhardt.  Support Vector Machines For Pattern Recognition , 2006 .

[9]  Thomas Vetter,et al.  A morphable model for the synthesis of 3D faces , 1999, SIGGRAPH.

[10]  N. Otsu.  A threshold selection method from gray level histograms , 1979 .

[11]  José F. Vélez,et al.  Face recognition using 3D surface extracted descriptors , 2003 .

[12]  Alejandro F. Frangi,et al.  Two-dimensional PCA: a new approach to appearance-based face representation and recognition , 2004 .