Recognition of Facial Expression via Kernel PCA Network

Abstract:

In this work, a kernel principle component analysis network (KPCANet) is proposed for classification of the facial expression in unconstrained images, which comprises only the very basic data processing components: cascaded kernel principal component analysis (KPCA), binary hashing, and block-wise histograms. In the proposed model, KPCA is employed to learn multistage filter banks. It is followed by simple binary hashing and block histograms for indexing and pooling. For comparison and better understanding, We have tested these basic networks extensively on many benchmark visual datasets ( such as the JAFFE [13] database, the CMU AMP face expression database, a part of the Extended Cohn-Kanade (CK+) database), The results demonstrate the potential of the KPCANet serving as a simple but highly competitive baseline for facial expression recognition.

• Periodical: Applied Mechanics and Materials (Volumes 631-632)
• Pages: 498-501
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.631-632.498
• Online since: September 2014
• Authors: De Kun Hu, An Sheng Ye*, Li Li, Li Zhang
• Keywords: Deep Learning, Facial Expression, Principle Component Analysis Network

References

[1] T. Chan, K. Jia, S. Gao, J. Lu, Z. Zeng, Y. Ma: PCANet: A Simple Deep Learning Baseline for Image Classification, CoRR abs/1404. 3606 (2014).

DOI: 10.1109/tip.2015.2475625

[2] Q. Wang, Kernel Principal Component Analysis and its Applications in Face Recognition and Active Shape Models, arXiv: 1207. 3538v2 [cs. CV] 23 Apr (2014).

[3] A. J. Calder, A. M. Burton, P. Miller, A. W. Young, and S. Akamatsu, A principal component analysis of facial expression, Vision Research, vol. 41 (2001): 1179–1208.

DOI: 10.1016/s0042-6989(01)00002-5

[4] B. Raducanu, J. Vitria, Online nonparametric discriminant analysis for incremental subspace learning and recognition, Pattern Anal Applic, vol. 11(2008): 259-268.

DOI: 10.1007/s10044-008-0131-0

[5] S.C. Tai and H.F. Huang, Facial expression recognition in video sequences, Sixth Int'l Symposium on Neural Network (2009): 1026-1033.

[6] Y. Shinohara and N. Otsu, Facial Expression Recognition Using Fisher Weight Maps, IEEE Conf. on Automatic Face and Guesture Recognition (2004): 499-504.

DOI: 10.1109/afgr.2004.1301582

[7] C. F. Shan, S. G. Gong, W. Peter, Facial expression recognition based on Local Binary Patterns: A comprehensive study, Image and Vision Computing vol. 19 (2009): 803–816.

DOI: 10.1016/j.imavis.2008.08.005

[8] H. Soyel, H. Demirel, Facial expression recognition based on discriminative scale invariant feature transform, Electronics Letters, vol. 46(2010).

DOI: 10.1049/el.2010.0092

[9] G. Du, F. Su, A. Cai, Face recognition using SURF features, Pattern Recognition and Computer Vision, vol. 7496(2009): 749628. 1- 749628. 7.

[10] T. Danisman, I. M. Bilasco, J. Martinet, C. Djeraba Intelligent pixels of interest selection with application to facial expression recognition using multilayer perceptron, Signal Processing Vol. 93 (2013): 1547–1556.

DOI: 10.1016/j.sigpro.2012.08.007

[11] A. Khan, A. Meyer, H. Konik, S. Bouakaz, Framework for reliable, real-time facial expression recognition for low resolution images, Pattern Recognition Letters vol. 34 (2013) : 1159-1168.

DOI: 10.1016/j.patrec.2013.03.022

[12] Y. Sun, X. Wang and X. Tang, Deep Convolutional Network Cascade for Facial Point Detection, CVPR (2013).