Learning Salient Features for Real-Time Face Verification

We propose a novel person veriication system for real-time face identiication. The main features of the system include accurate registration of face images using a robust form of correlation, a framework for global registration of a face database using a minimum spanning tree algorithm and a method for selecting a subset of features optimal for discrimination between clients and impostors. We present results obtained through experiments on a large database with 295 subjects and show that the method is performing well in comparison with two standard methods based on elastic graph matching.

[1]  J. Kittler,et al.  Robust motion analysis , 1994, 1994 Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.

[2]  Roberto Brunelli,et al.  Robust estimation of correlation with applications to computer vision , 1995, Pattern Recognit..

[3]  David Beymer,et al.  Face recognition under varying pose , 1994, 1994 Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.

[4]  Jiri Matas,et al.  Acquisition of a Large Database for Biometric Identity Verification , 1998 .

[5]  C. D. Gelatt,et al.  Optimization by Simulated Annealing , 1983, Science.

[6]  Jiri Matas,et al.  Fast face localisation and verification , 1999, Image Vis. Comput..

[7]  Jiri Matas,et al.  Saliency-Based Robust Correlation for Real-Time Face Registration and Verification , 1998, BMVC.