Face Recognition and Expression Classification

In this chapter, faces are detected and facial features are located from video and still images. 'NRC-IIT Facial video database' is used as image sequences and 'face 94 color image database' is used for still images. Skin pixels and non-skin pixels are separated and skin region identification is done by RGB color space. From the extracted skin region, skin pixels are grouped to some meaningful groups to identify the face region. From the face region, facial features are located using seg- mentation technique. Orientation correction is done by using eyes. Parameters like inter eye distance, nose length, mouth position, and DCT coefficients are computed which is used for a RBF based neural network.

[1]  Marian Stewart Bartlett,et al.  Face recognition by independent component analysis , 2002, IEEE Trans. Neural Networks.

[2]  Michael J. Lyons,et al.  Coding facial expressions with Gabor wavelets , 1998, Proceedings Third IEEE International Conference on Automatic Face and Gesture Recognition.

[3]  Franc Solina,et al.  An Automatic Human Face Detection Method , 1999 .

[4]  Jing Xiao,et al.  Meticulously detailed eye region model and its application to analysis of facial images , 2006, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[5]  Alfred C. Weaver,et al.  Biometric authentication , 2006, Computer.

[6]  Rama Chellappa,et al.  Human and machine recognition of faces: a survey , 1995, Proc. IEEE.

[7]  A. N. Rajagopalan,et al.  Human Face Detection in Cluttered Color Images Using Skin Color, Edge Information , 2002, ICVGIP.

[8]  Franc Solina,et al.  15 seconds of fame - an interactive, computer-vision based art installation , 2002, 7th International Conference on Control, Automation, Robotics and Vision, 2002. ICARCV 2002..

[9]  Dmitry O. Gorodnichy,et al.  Video-based framework for face recognition in video , 2005, The 2nd Canadian Conference on Computer and Robot Vision (CRV'05).

[10]  Tat-Jun Chin,et al.  Face Recognition From Video using Active Appearance Model Segmentation , 2006, 18th International Conference on Pattern Recognition (ICPR'06).

[11]  Qiang Ji,et al.  Facial Action Unit Recognition by Exploiting Their Dynamic and Semantic Relationships , 2007, IEEE Transactions on Pattern Analysis and Machine Intelligence.