342 A Wavelet-Transform Based Asker Identification System for Smart Multi-point Tele-conferences

This paper proposes a wavelet-based asker identification system for smart multi-point tele-conferences. Our system is composed of three processors. The first processor is called an “ask” action detector, which is used to decide whether an “ask” action is occurring. If an “ask” action is detected, the input image is sent to the face detector that detects the human face from the complex background. The detected face is fed to a wavelet-based face identification processor to recognize the asker.

[1]  Sun-Yuan Kung,et al.  Face recognition/detection by probabilistic decision-based neural network , 1997, IEEE Trans. Neural Networks.

[2]  Roberto Brunelli,et al.  Face Recognition: Features Versus Templates , 1993, IEEE Trans. Pattern Anal. Mach. Intell..

[3]  Chung-Lin Huang,et al.  Human Face Recognition from A Single Front View , 1992, Int. J. Pattern Recognit. Artif. Intell..

[4]  Ke Liu,et al.  A robust algebraic method for human face recognition , 1992, Proceedings., 11th IAPR International Conference on Pattern Recognition. Vol.II. Conference B: Pattern Recognition Methodology and Systems.

[5]  Stéphane Mallat,et al.  A Theory for Multiresolution Signal Decomposition: The Wavelet Representation , 1989, IEEE Trans. Pattern Anal. Mach. Intell..