Novel methods for real-time 3D facial recognition

In this paper we discuss our approach to real-time 3D face recognition. We argue the need for real time operation in a realistic scenario and highlight the required pre- and post-processing operations for effective 3D facial recognition. We focus attention to some operations including face and eye detection, and fast post-processing operations such as hole filling, mesh smoothing and noise removal. We consider strategies for hole filling such as bilinear and polynomial interpolation and Laplace and conclude that bilinear interpolation is preferred. Gaussian and moving average smoothing strategies are compared and it is shown that moving average can have the edge over Gaussian smoothing. The regions around the eyes normally carry a considerable amount of noise and strategies for replacing the eyeball with a spherical surface and the use of an elliptical mask in conjunction with hole filling are compared. Results show that the elliptical mask with hole filling works well on face models and it is simpler to implement. Finally performance issues are considered and the system has demonstrated to be able to perform real-time 3D face recognition in just over 1s 200ms per face model for a small database.

[1]  Wei Zhao,et al.  A Robust Hole-Filling Algorithm for Triangular Mesh , 2007, CAD/Graphics.

[2]  Willie Brink,et al.  3D modelling and recognition , 2006 .

[3]  Patrick J. Flynn,et al.  A survey of approaches to three-dimensional face recognition , 2004, ICPR 2004.

[4]  Lyuba Alboul,et al.  Producing animations from 3D face scans , 2005 .

[5]  V. Pisarevsky,et al.  Intel's Computer Vision Library: applications in calibration, stereo segmentation, tracking, gesture, face and object recognition , 2000, Proceedings IEEE Conference on Computer Vision and Pattern Recognition. CVPR 2000 (Cat. No.PR00662).

[6]  Gordon Erlebacher,et al.  A novel technique for face recognition using range imaging , 2003, Seventh International Symposium on Signal Processing and Its Applications, 2003. Proceedings..

[7]  Willie Brink,et al.  Indexing Uncoded Stripe Patterns in Structured Light Systems by Maximum Spanning Trees , 2008, BMVC.

[8]  Manuel Menezes de Oliveira Neto,et al.  Filling holes on locally smooth surfaces reconstructed from point clouds , 2007, Image Vis. Comput..

[9]  Lyuba Alboul,et al.  Methods for Indexing Stripes in Uncoded Structured Light Scanning Systems , 2004, WSCG.

[10]  Willie Brink,et al.  Issues in fast 3D reconstruction from video sequences , 2007 .

[11]  Willie Brink,et al.  Fast 3D reconstruction and recognition , 2008 .

[12]  Gaile G. Gordon,et al.  Face recognition based on depth and curvature features , 1992, Proceedings 1992 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[13]  Manuel Menezes de Oliveira Neto,et al.  A hole-filling strategy for reconstruction of smooth surfaces in range images , 2003, 16th Brazilian Symposium on Computer Graphics and Image Processing (SIBGRAPI 2003).