Boosted Independent Features for Face Expression Recognition

Independent Component Analysis (ICA) is used widely to extract statistical independent features for analysis and discrimination in recent years. But its random properties make it very difficult to test the efficiency and validation of the extracted independent features. In this paper, we propose a new method called BoostedICA to solve such problems by running ICA several times and boosting the selected independent components. Because of the local extremum question in calculating independent component, several times of running could get the more valid components with larger probability. The AdaBoost algorithm can guarantee the discriminating efficient of the selected features from the statistical theory. The proposed method achieves both computational efficiency and accuracy through optimizing extracting and choosing features. Finally we describe face expression recognition experiments on person-dependent and person-independent. The experimental results of 97.5% and 86% recognition rate respectively show that our method has better performance compared with other methods.

[1]  Nobuyuki Otsu,et al.  Facial expression recognition using Fisher weight maps , 2004, Sixth IEEE International Conference on Automatic Face and Gesture Recognition, 2004. Proceedings..

[2]  Michael J. Lyons,et al.  Automatic Classification of Single Facial Images , 1999, IEEE Trans. Pattern Anal. Mach. Intell..

[3]  Terrence J. Sejnowski,et al.  An Information-Maximization Approach to Blind Separation and Blind Deconvolution , 1995, Neural Computation.

[4]  Harold Szu,et al.  A local face statistics recognition methodology beyond ICA and/or PCA , 1999, IJCNN'99. International Joint Conference on Neural Networks. Proceedings (Cat. No.99CH36339).

[5]  Josef Kittler,et al.  Independent component analysis in a facial local residue space , 2003, 2003 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2003. Proceedings..

[6]  Ioannis Pitas,et al.  Application of non-negative and local non negative matrix factorization to facial expression recognition , 2004, ICPR 2004.

[7]  Chengjun Liu,et al.  Independent component analysis of Gabor features for face recognition , 2003, IEEE Trans. Neural Networks.

[8]  Narendra Ahuja,et al.  Face recognition using feature extraction based on independent component analysis , 2002, Proceedings. International Conference on Image Processing.

[9]  Andrzej Cichocki,et al.  Robust learning algorithm for blind separation of signals , 1994 .

[10]  Yoram Singer,et al.  Improved Boosting Algorithms Using Confidence-rated Predictions , 1998, COLT' 98.

[11]  Aapo Hyvärinen,et al.  A Fast Fixed-Point Algorithm for Independent Component Analysis , 1997, Neural Computation.

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

[13]  Aapo Hyvärinen,et al.  Validating the independent components of neuroimaging time series via clustering and visualization , 2004, NeuroImage.

[14]  Yoav Freund,et al.  A decision-theoretic generalization of on-line learning and an application to boosting , 1997, EuroCOLT.

[15]  J. Friedman.  Special Invited Paper-Additive logistic regression: A statistical view of boosting , 2000 .

[16]  Manabu Kotani,et al.  Feature extraction using supervised independent component analysis by maximizing class distance , 2002, Proceedings of the 9th International Conference on Neural Information Processing, 2002. ICONIP '02..

[17]  Bo Wu,et al.  Real time facial expression recognition with AdaBoost , 2004, Proceedings of the 17th International Conference on Pattern Recognition, 2004. ICPR 2004..

[18]  Aapo Hyvärinen,et al.  Fast and robust fixed-point algorithms for independent component analysis , 1999, IEEE Trans. Neural Networks.

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