Hierarchical multistream recognition of facial expressions
Chibelushi, C.C. and Bourel, F. (2004) Hierarchical multistream recognition of facial expressions. IEE Proceedings - Vision, Image, and Signal Processing, 151 (4). pp. 307-313. ISSN 1350245XFull text not available from this repository.
Abstract or description
Achieving optimal recognition accuracy, particularly under conditions of input data variability, is a challenge for automatic facial expression recognition. However, little research has been devoted to investigating the robustness of automatic expression recognition under adverse conditions. A facial expression modelling approach is proposed for enhancing the robustness of expression recognition. The approach is founded on hierarchical state-based modelling of streams that represent spatially localised expression dynamics. Experimental assessment shows that the proposed model achieves high and stable recognition accuracy over a range of input data degradation. Moreover, interstream coupling as well as the inclusion of adaptive estimation of model reliability and credibility are shown to make a positive contribution to recognition accuracy.
|Subjects:||G400 Computer Science|
|Faculty:||Faculty of Computing, Engineering and Sciences > Computing|
|Depositing User:||Claude CHIBELUSHI|
|Date Deposited:||10 Apr 2013 19:18|
|Last Modified:||10 Apr 2013 19:18|
Actions (login required)