Recognizing facial expression based on discriminative multi-order Two Dimensions Fractional Fourier Transform

Two Dimensions Fractional Fourier Transform (2D-FrFT) is a powerful tool for feature extraction in facial expression recognition. However, a single order 2D-FrFT feature is not effective enough. In this paper, it proposes a facial expression recognition system based on multi-order with 2D-FrFT features. Moreover, a multi-feature fusion algorithm which is named Discriminative Multi-set Canonical Correlation Analysis (DMCCA) is deduced. Fusion of multi-order 2D-FrFT features by DMCCA can significantly improve the recognition performance, due to increased amount of discriminative information. More important, an objective function is defined to find the optimal 2D-FrFT orders group fused by DMCCA. Experiment results demonstrate the effectiveness of the method.

[1]  Ling Guan,et al.  Recognizing Human Emotional State From Audiovisual Signals , 2008, IEEE Transactions on Multimedia.

[2]  Jian Yang,et al.  Feature fusion: parallel strategy vs. serial strategy , 2003, Pattern Recognit..

[3]  John Shawe-Taylor,et al.  Canonical Correlation Analysis: An Overview with Application to Learning Methods , 2004, Neural Computation.

[4]  Gozde Bozdagi Akar,et al.  Digital computation of the fractional Fourier transform , 1996, IEEE Trans. Signal Process..

[5]  Cheong Hee Park,et al.  Analysis of correlation based dimension reduction methods , 2011, Int. J. Appl. Math. Comput. Sci..

[6]  Lei Gao,et al.  Recognizing Human Emotional State Based on the Phase Information of the Two Dimensional Fractional Fourier Transform , 2010, PCM.

[7]  P. Ekman.  Emotion in the human face , 1982 .

[8]  P. Ekman.  Unmasking The Face , 1975 .

[9]  Wee Ser,et al.  Speech Emotion Recognition Using Canonical Correlation Analysis and Probabilistic Neural Network , 2008, 2008 Seventh International Conference on Machine Learning and Applications.

[10]  Pengfei Shi,et al.  Discriminative Canonical Correlation Analysis with Missing Samples , 2009, 2009 WRI World Congress on Computer Science and Information Engineering.

[11]  Jian Yang,et al.  Generalized K-L transform based combined feature extraction , 2002, Pattern Recognit..

[12]  Chengjun Liu,et al.  A shape- and texture-based enhanced Fisher classifier for face recognition , 2001, IEEE Trans. Image Process..

[13]  Chong-sun Kim.  Canonical Analysis of Several Sets of Variables , 1973 .

[14]  Lei Gao,et al.  Recognizing Human Emotional State Based on the 2D-FrFT and FLDA , 2009, 2009 2nd International Congress on Image and Signal Processing.

[15]  Ling Guan,et al.  Recognizing Human Emotional State From Audiovisual Signals* , 2008, IEEE Transactions on Multimedia.

[16]  H. Hotelling.  Relations Between Two Sets of Variates , 1936 .