Emotion recognition using Principal Component Analysis with Singular Value Decomposition

Emotion recognition plays vital role in Human Computer Interface. This paper focuses on facial expression to identify seven universal human emotions such as, happy, disgust, neutral, anger, sad, surprise and fear. This is carried out by trying to extract unique facial expression features among emotions using Principal Component Analysis with Singular Value Decomposition and Euclidean Distance Classifier. Using public database Japanese Female Facial Expression (JAFFE) recognition is obtained nearly 78.57%. Recognition rate and Accuracy of various expressions using Principal Component Analysis alone and Principal Component Analysis with Singular Value Decomposition is compared.

[1]  Alejandro F. Frangi,et al.  Two-dimensional PCA: a new approach to appearance-based face representation and recognition , 2004 .

[2]  M. Turk,et al.  Eigenfaces for Recognition , 1991, Journal of Cognitive Neuroscience.

[3]  Ying Zilu,et al.  Combining LBP and Adaboost for facial expression recognition , 2008, 2008 9th International Conference on Signal Processing.

[4]  Ching-Chih Tsai,et al.  Interactive emotion recognition using Support Vector Machine for human-robot interaction , 2009, 2009 IEEE International Conference on Systems, Man and Cybernetics.

[5]  Jagath C. Rajapakse,et al.  Color channel encoding with NMF for face recognition , 2004, 2004 International Conference on Image Processing, 2004. ICIP '04..

[6]  Marian Stewart Bartlett,et al.  Classifying Facial Actions , 1999, IEEE Trans. Pattern Anal. Mach. Intell..

[7]  Takeo Kanade,et al.  Automated facial expression recognition based on FACS action units , 1998, Proceedings Third IEEE International Conference on Automatic Face and Gesture Recognition.