HYBRID-BOOSTLEARNINGFOR MULTI-POSEFACEDETECTIONAND FACIAL EXPRESSIONRECOGNITION

This paper proposes anovel multi-class hybrid-boost learning algorithm formulti-pose facedetection andfacial expression recognition. Thissystem detects humanfaceindifferent sizes, various poses, partial-occlusion, anddifferent expressions. The contribution ofthis paperisthehybrid boosting algorithm combining theHaar-like (local) features andGabor-like (global) features. Theexperimental results showthatoursystem has better performance thantheothers.

[1]  Paul A. Viola,et al.  Rapid object detection using a boosted cascade of simple features , 2001, Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001.

[2]  Stan Z. Li,et al.  FloatBoost learning and statistical face detection , 2004, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[3]  Hyeonjoon Moon,et al.  The FERET Evaluation Methodology for Face-Recognition Algorithms , 2000, IEEE Trans. Pattern Anal. Mach. Intell..

[4]  Léon J. M. Rothkrantz,et al.  Facial Expression Recognition with Relevance Vector Machines , 2005, 2005 IEEE International Conference on Multimedia and Expo.

[5]  Myung Jin Chung,et al.  Efficient rectangle feature extraction for real-time facial expression recognition based on AdaBoost , 2005, 2005 IEEE/RSJ International Conference on Intelligent Robots and Systems.