Title :
Facial gesture recognition for interactive applications
Author :
Algorri, María Elena ; Escobar, Alejandra
Author_Institution :
Dept. of Digital Syst., Instituto Tecnologico Autonomo de Mexico, Mexico
Abstract :
We present an attractive methodology for the compression of facial gestures that can be used to drive interaction in real time applications. Using the eigenface method we build compact representation spaces for a variety of facial gestures. These compact spaces are the so called eigenspaces. We do real time tracking and segmentation of facial features from video images and then use the eigenspaces to find compact descriptors of the segmented features. We use the system for an avatar videoconference application where we achieve real time interactivity with very limited bandwidth requirements. The system can also be used as a hands free man-machine interface.
Keywords :
eigenvalues and eigenfunctions; face recognition; feature extraction; gesture recognition; image segmentation; interactive systems; teleconferencing; video signal processing; avatar videoconference application; eigenface method; eigenspaces; facial feature segmentation; facial gesture compression; facial gesture recognition; interactive application; man-machine interface; real-time application; real-time tracking; video images; Avatars; Bandwidth; Face recognition; Facial features; Image coding; Image segmentation; Real time systems; User interfaces; Video compression; Videoconference;
Conference_Titel :
Computer Science, 2004. ENC 2004. Proceedings of the Fifth Mexican International Conference in
Print_ISBN :
0-7695-2160-6
DOI :
10.1109/ENC.2004.1342605
