Appearance-Based Person Recognition for Surveillance Applications

This paper presents an original system for recognizing persons based on their appearance. Thus, it is especially suitable to surveillance scenarios, where biometric information might not be available. Different visual low level features in combination with different supervised learning methods are examined in order to built a robust system. Furthermore, complementary features are fused using postmapping fusion concepts to improve the reliability. The experiments show that the system is able to distinguish a large number of people and can be used for different applications.

[1]  B. S. Manjunath,et al.  Introduction to mpeg-7 , 2002 .

[2]  Tomaso A. Poggio,et al.  Full-body person recognition system , 2003, Pattern Recognit..

[3]  Conrad Sanderson,et al.  Automatic Person Verification Using Speech and Face Information , 2003 .

[4]  Thomas Sikora,et al.  Comparison of static background segmentation methods , 2005, Visual Communications and Image Processing.

[5]  John H. L. Hansen,et al.  Identifying in-set and out-of-set speakers using neighborhood information , 2004, 2004 IEEE International Conference on Acoustics, Speech, and Signal Processing.

[6]  Michal Strzelecki,et al.  Texture Analysis Methods - A Review , 1998 .

[7]  M. Hahnel,et al.  Color and texture features for person recognition , 2004, 2004 IEEE International Joint Conference on Neural Networks (IEEE Cat. No.04CH37541).