Facial Expression Recognition Based on Orthogonal Nonnegative CP Factorization

Abstract:

Facial Expression recognition based on Non-negative Matrix Factorization (NMF) requires the object images should be vectorized. The vectorization leads to information loss, since local structure of the images is lost. Moreover, NMF can not guarantee the uniqueness of the decomposition. In order to remedy these limitations, the facial expression image was considered as a high-order tensor, and an Orthogonal Non-negative CP Factorization algorithm (ONNCP) was proposed. With the orthogonal constrain, the low-dimensional presentations of samples were non-negative in ONNCP. The convergence characteristic of the algorithm was proved. The experiments indicate that, compared with other non-negative factorization algorithms, the algorithm proposed in the paper reduces the redundancy of the base image and has better recognition rate in facial expression recognition.

• Periodical: Advanced Materials Research (Volumes 143-144)
• Pages: 111-115
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.143-144.111
• Online since: October 2010
• Authors: Chang Liu, Kun He, Ji Liu Zhou, Yan Li Zhu
• Keywords: Candecomp/Parafac Decomposition, Facial Expression Recognition, Non-Negative Factorization, Orthogonal Constraint

References

[1] G. Ting, H. Tong-sen, and T. Xian-zhong, Human face expression recognition based on within-class modular PCA. Mechanical & Electrical Engineering Magazine, (2009).

[2] S. Miao, and J. Zhang, Facial expression recognition based on 2 D-DWT and ICA. Jisuanji Gongcheng yu Yingyong(Computer Engineering and Applications), Vol. 44 (2008), pp.188-191.

[3] Y. Cheon, and D. Kim, Natural facial expression recognition using differential-AAM and manifold learning. Pattern Recognition, Vol. 42 (2009), pp.1340-1350.

DOI: 10.1016/j.patcog.2008.10.010

[4] L. Zilu Ying, J. Gan, and S. He, Facial Expression Recognition with Local Binary Pattern and Laplacian Eigenmaps. in Proceedings of the 5th International Conference on Intelligent Computing, (2009), p.228.

DOI: 10.1007/978-3-642-04070-2_26

[5] I. Buciu, and I. Pitas, NMF, LNMF, and DNMF modeling of neural receptive fields involved in human facial expression perception. Journal of Visual Communication and Image Representation, Vol. 17 (2006), pp.958-969.

DOI: 10.1016/j.jvcir.2006.06.001

[6] M. Turk, and A. Pentland, Eigenfaces for Recognition. Journal of Cognitive Neuroscience, Vol. 3 (1991), pp.71-86.

[7] D. Lee, and H. Seung, Learning the parts of objects by non-negative matrix factorization. Nature, Vol. 401 (1999), pp.788-791.

DOI: 10.1038/44565

[8] D. Donoho, and V. Stodden, When does non-negative matrix factorization give a correct decomposition into parts. Advances in Neural Information Processing Systems, Vol. 16 (2004), pp.1141-1148.

[9] T. Van de Cruys, A Non-negative Tensor Factorization Model for Selectional Preference Induction. GEMS: GEometrical Models of Natural Language Semantics, (2009), p.83.

DOI: 10.3115/1705415.1705426

[10] S. Zafeiriou, Algorithms for Nonnegative Tensor Factorization. Tensors in Image Processing and Computer Vision, (2009), p.105.

DOI: 10.1007/978-1-84882-299-3_5

[11] S. Zafeiriou, Discriminant Nonnegative Tensor Factorization Algorithms. IEEE Transactions on Neural Networks, Vol. 20 (2009), pp.217-235.

DOI: 10.1109/tnn.2008.2005293

[12] Z. Yang, and J. Laaksonen, Multiplicative updates for non-negative projections. Neurocomputing, Vol. 71 (2007), pp.363-373.

DOI: 10.1016/j.neucom.2006.11.023

[13] D. Lee, and H. Seung, Algorithms for non-negative matrix factorization. Advances in Neural Information Processing Systems, (2001), pp.556-562.

[14] S. Li, X. Hou, H. Zhang, and Q. Cheng, Learning spatially localized, parts-based representation. in Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, (2001), pp.1-6.

DOI: 10.1109/cvpr.2001.990477

[15] T. Hazan, S. Polak, and A. Shashua, Sparse image coding using a 3D non-negative tensor factorization. in Proceedings of International Conference of Computer Vision, (2005), pp.50-57.

DOI: 10.1109/iccv.2005.228