3D Face Hierarchical Recognition Based on Geometric and Curvature Features

A method of 3D face hierarchical recognition based on geometric and curvature features is proposed. Firstly, by normalizing the original scattered 3D face point cloud, much less amount of the points is acquired, which still contain the main characteristics of the face. Secondly, by calculating and analyzing the curvatures of pre-processed 3D face profiles, which are extracted from the normalized point cloud, the facial feature points are located. Finally, a feature model formed by the profiles and feature points is used for 3D face hierarchical recognition. Our results show that the hierarchical recognition improves recognition accuracy, and it is more robust on face expressions.

[1]  I. Masuda,et al.  3D facial image analysis for human identification , 1992, [1992] Proceedings. 11th IAPR International Conference on Pattern Recognition.

[2]  Patrick J. Flynn,et al.  A survey of approaches and challenges in 3D and multi-modal 3D + 2D face recognition , 2006, Comput. Vis. Image Underst..

[3]  Behzad Dariush,et al.  Spatiotemporal analysis of face profiles: detection, segmentation, and registration , 1998, Proceedings Third IEEE International Conference on Automatic Face and Gesture Recognition.

[4]  Alexander M. Bronstein,et al.  Three-Dimensional Face Recognition , 2005, International Journal of Computer Vision.

[5]  Zhaohui Wu,et al.  Exploring Facial Expression Effects in 3D Face Recognition Using Partial ICP , 2006, ACCV.

[6]  Some properties of Bφ-splines , 2009 .

[7]  Wang Guo-yin.  Facial feature extraction based on curvature and texture , 2008 .

[8]  Andrea F. Abate,et al.  2D and 3D face recognition: A survey , 2007, Pattern Recognit. Lett..