Improving Pose Manifold and Virtual Images Using Bidirectional Neural Networks in Face Recognition Using Single Image per Person
Subject Areas : electrical and computer engineering
F.
Abdolali
1
S. A.
Seyed Salehi
2
Abstract :
In this article, for the purpose of improving neural network models applied in face recognition using single image per person, a bidirectional neural network inspired of neocortex functional model is presented. In the proposed model, recognition is not performed in a single stage, but via two bottom-up and top-down phases and the recognition results of first stage is used for model adaptation. We have applied this novel adapting model in combination with clustering person and pose information technique to separate person and pose information and to estimate corresponding manifolds. To increase the number of training samples in the classifier neural network, virtual views of frontal images in the test dataset are synthesized using estimated manifolds. Training classifier network via virtual images obtained from bidirectional network, gives an accuracy rate of 85.45% on the test dataset which shows 1.82% improvement in accuracy of face recognition compared to training classifier with virtual images obtained from clustering person and pose information network.
[1] X. Zhang and Y. Gao, "Face recognition across pose: a review," Pattern Recognition, vol. 42, no. 11, pp. 2876-2896, Nov. 2009.
[2] T. Stonham, "Practical face recognition and verification with WISARD," Aspects of Face Processing, pp. 426-441, 1984.
[3] S. H. Lin, S. Y. Kung, and L. J. Lin, "Face recognition/detection by probabilistic decision - based neural network," IEEE Trans. Neural Network, vol. 8, no. 1, pp. 114-132, Jan. 1997.
[4] S. Lawrence, C. L. Giles, A. C. Tsoi, and A. D. Back, "Face recognition: a convolutional neural-network approach," IEEE Trans. Neural Network, vol. 8, no. 1, pp. 98-113, Jan.1997.
[5] Y. W. Wong, K. P. Seng, and L. M. Ang, "Radial basis function neural network with incremental learning for face recognition," IEEE Trans. Syst. Man Cybern. B, vol. 41, no. 4, pp. 940-949, Aug. 2011.
[6] F. Abdolali and S. Seyyedsalehi, "Face recognition from a single image per person using deep architecture neural networks," in Proc. 3rd Int. Conf. on Computer and Electrical Engineering, Chengdu, vol. 1, pp. 70-73, Nov. 2010.
[7] ن. داداشی، بازشناسی چهره با استفاده از يک تصوير از هر فرد، پايان‌نامه کارشناسی ارشد، دانشگاه صنعتی اميرکبير، دانشکده مهندسی پزشکی، دی 1387.
[8] ع. سيدصالحي، افزايش کارآيي بازشناخت الگوي شبکه‌هاي عصبي جلوسو از طريق توسعه روش‌هايي براي دوسويه‌کردن عملکرد آنها، گزارش طرح پژوهشي، دانشگاه صنعتي اميرکبير، دانشکده مهندسي پزشکي، 1383.
[9] A. Leila and S. Seyyedsalehi, "Modeling phones coarticulation effects in a neural network based speech recognition system," in Proc. INTERSPEECH-2004, vol. 1, pp. 1657-1660, Oct. 2004.
[10] I. Nejadgholi and S. Seyyedsalehi, "Nonlinear normailization of input patterns to speaker variability in speech recognition neural networks," Neural Computing & Applications, vol. 18, no. 1, pp. 45-55, Jan. 2009.
[11] M. M. Mesulam, "From sensation to cognition," Brain, vol. 121, no. 6, pp. 1013-1052, Jun. 1998.
[12] E. Koerner and G. Matsumoto, "Cortical architecture and self - referential control for brain - like computation, a new approach to understanding how the brain organizes computation," IEEE Eng. in Medicine and Biology Magazine, vol. 21, no. 5, pp. 121-133, Sep./Oct. 2002.
[13] E. Koerner, H. Tsujino, and T. Masutani, "A cortical - type modular neural network for hypothetical reasoning," Neural Networks, vol. 10, no. 5, pp. 791-814, Jul. 1997.
[14] E. Koerner and et al., "A model of computation in neocortical architecture," Neural Networks, vol. 12, no. 12, pp. 989-1005, Oct. 1999.
[15] J. Ghosen and Y. Bengio, "Bias learning, knowledge sharing," IEEE Trans. on Neural Networks, vol. 14, no. 4, pp. 748-765, Jul. 2003.
[16] J. Aghajanian and S. J. D. Prince, "Face pose estimation in uncontrolled environments," in Proc. British Machine Vision Conf., 2009.