KSII Transactions on Internet and Information Systems (TIIS)

Korean Society for Internet Information (한국인터넷정보학회)
권호 표지
DOI QR코드

DOI QR Code

Few Samples Face Recognition Based on Generative Score Space

  • Wang, Bin (College of Information, Mechanical and Electrical Engineering, Shanghai Normal University) ;
  • Wang, Cungang (School of Computer Science, Liaocheng University) ;
  • Zhang, Qian (College of Information, Mechanical and Electrical Engineering, Shanghai Normal University) ;
  • Huang, Jifeng (College of Information, Mechanical and Electrical Engineering, Shanghai Normal University)
  • Received : 2016.07.19
  • Accepted : 2016.10.31
  • Published : 2016.12.31
Download PDF
⟨ Previous Next ⟩

Abstract

Few samples face recognition has become a highly challenging task due to the limitation of available labeled samples. As two popular paradigms in face image representation, sparse component analysis is highly robust while parts-based paradigm is particularly flexible. In this paper, we propose a probabilistic generative model to incorporate the strengths of the two paradigms for face representation. This model finds a common spatial partition for given images and simultaneously learns a sparse component analysis model for each part of the partition. The two procedures are built into a probabilistic generative model. Then we derive the score function (i.e. feature mapping) from the generative score space. A similarity measure is defined over the derived score function for few samples face recognition. This model is driven by data and specifically good at representing face images. The derived generative score function and similarity measure encode information hidden in the data distribution. To validate the effectiveness of the proposed method, we perform few samples face recognition on two face datasets. The results show its advantages.

Keywords

References

  1. Z. Cui, HongChang, ShiguangShan, BingpengMac, and XilinChen, "Joint sparse representation for video-based face recognition," Neurocomputing, vol. 135, pp. 306-312, July, 2014. https://doi.org/10.1016/j.neucom.2013.12.004
  2. H. Shim, "Probabilistic approach to realistic face synthesis with a single uncalibrated image," IEEE Trans. Image Processing, vol. 21, no. 8, pp. 3784-3793, 2012. https://doi.org/10.1109/TIP.2012.2192125
  3. Hu H, Klare B F, and Bonnen K, et al, "Matching Composite Sketches to Face Photos: A Component-Based Approach," IEEE Transactions on Information Forensics & Security, vol. 8, no. 1, pp. 191-204, 2013. https://doi.org/10.1109/TIFS.2012.2228856
  4. Z. Lei, and S. Li, "Learning discriminant face descriptor for face recognition," in Proc. of Asian Conference on Computer Vision, vol. 7725, no. 2, pp. 748-759, 2012.
  5. N.-S. Vu, and A. Caplier, "Enhanced patterns of oriented edge magnitudes for face recognition and image match-ing," IEEE Trans. on Image Processing, vol. 21, no. 3, pp. 1352-1365, 2012. https://doi.org/10.1109/TIP.2011.2166974
  6. Xie S, Shan S, and Chen X, et al, "Fusing local patterns of Gabor magnitude and phase for face recognition," IEEE Transactions on Image Processing, vol. 19, no. 5, pp. 1349-1361, 2010. https://doi.org/10.1109/TIP.2010.2041397
  7. Jolliffe I T, "Principal Component Analysis," Springer Berlin, vol. 87, no. 100, pp. 41-64, 2015.
  8. Westlake C, Mountain R W, and Paton T A L, "Factored Shapes and Appearances for Parts-based Object Understanding," in Proc. of IEE - Part I: General, vol. 101, no. 132, pp. 367-368, 2011. https://doi.org/10.1049/pi-1.1954.0086
  9. B. Olshausen, and D. Field, "Sparse coding with an overcomplete basis set: A strategy employed by V1?," Vision Research, vol. 37, no. 23, pp. 3311-3325, 1997. https://doi.org/10.1016/S0042-6989(97)00169-7
  10. D. Lee, and H. Seung, "Learning the parts of objects by non-negative matrix factorization," Nature, vol. 401, no. 6755, pp. 788-791, 1999. https://doi.org/10.1038/44565
  11. D. Ross, and R. Zemel, "Learning parts-based representations of data," The Journal of Machine Learning Research , vol. 7, no. 3, pp. 2369-2397, 2006.
  12. R. Jenatton, G. Obozinski, and F. Bach, "Structured sparse principal component analysis," in Proc. of AISTATS, vol. 9, no. 2, 131-160, 2009.
  13. H. Zou, T. Hastie, and R. Tibshirani, "Sparse principal component analysis," Journal of Computational and Graphical Statistics, vol. 15, no. 2, pp. 265-286, 2006. https://doi.org/10.1198/106186006X113430
  14. T. D. Y. Jia, and M Salzmann, "Factorized latent spaces with structured sparsity," in Proc. of Neural Information Processing Systems, pp. 982-990, 2011.
  15. P. Luo, X. Wang, and X. Tang, "Hierarchical face parsing via deep learning," in Proc. of Computer Vision and Pattern Recognition, vol. 157, no. 10, pp. 2480-2487, 2012.
  16. S. Eslami and C. Williams, "Factored shapes and appearances for parts-based object understanding," in Proc. of British Machine Vision Conference, vol. 101, no. 132, pp. 367-368, 2011.
  17. Eisenstein J, Ahmed A, and Xing E P, "Sparse Additive Generative Models of Text," in Proc. of International Conference on Machine Learning, pp. 1041-1048, 2011.
  18. C. Archambeau and F. Bach, "Sparse probabilistic projections," in Proc. of Neural Information Processing Systems, pp. 73-80, 2008.
  19. G. Hinton, "Training products of experts by minimizing contrastive divergence," Neural Computation, vol. 14, no. 8, pp. 1771-1800, 2002. https://doi.org/10.1162/089976602760128018
  20. Beal M J, "Variational algorithms for approximate Bayesian inference," University College London, 2015.
  21. Levine, Richard A, and Casella, et al, "Implementations of the Monte Carlo EM Algorithm," Journal of Computational & Graphical Statistics, vol. 10, no. 10, pp. 422-439, 2001. https://doi.org/10.1198/106186001317115045
  22. J. Li, J. Pan, and S. Chu, "Kernel class-wise locality preserving projection," Information Sciences, vol. 178, no. 7, pp. 1825-1835, 2008. https://doi.org/10.1016/j.ins.2007.12.001
  23. J. Li, J. Pan, and S. Chu, "Kernel self-optimized locality preserving discriminant analysis for feature extraction and recognition," Neurocomputing, vol. 74, no. 17, pp. 3019-3027, 2011. https://doi.org/10.1016/j.neucom.2011.04.017
  24. Wright J, Yang A Y, and Ganesh A, et al. "Robust Face Recognition via Adaptive Sparse Representation," Cybernetics IEEE Transactions on, vol. 44, no. 12, pp. 2368 - 2378, 2014. https://doi.org/10.1109/TCYB.2014.2307067
  25. T. Sim, S. Baker, and M. Bsat, "The CMU pose, illumination, and expression (PIE) database," in Proc. of IEEE International Conference on Automatic Face and Gesture Recognition, Vol. 4, 2002.
  26. A. Martinez and R. Benavente, "The AR face database," CVC Technical Report.
  27. D. Cai, X. He, and J. Han, "Semi-supervised discriminant analysis," in Proc. of International Conference on Computer Vision, pp. 1-7, 2007.
  28. Y. Zhang and D. Yeung, "Semi-supervised discriminant analysis using robust path-based similarity," in Proc. of Computer Vision and Pattern Recognition, pp. 1-8, 2008.
  29. Y. Zhang and D.-Y. Yeung, "Semisupervised generalized discriminant analysis," IEEE Trans. on Neural Net-works, vol. 22, no. 8, pp. 1207-1217, 2011. https://doi.org/10.1109/TNN.2011.2156808
  30. Chatfield K, Lempitsky V, and Vedaldi A, et al., "The devil is in the details: an evaluation of recent feature encoding methods," in Proc. of British Machine Vision Conference, vol. 76, pp. 76.1-76.12, 2011.
  31. D. Cai, X. He, J. Han, and T. Huang, "Graph regularized nonnegative matrix factorization for data representation," IEEE Trans. on Pattern Analysis and Machine Intelligence, vol. 33, no. 8, pp. 1548 -1560, 2011. https://doi.org/10.1109/TPAMI.2010.231
  32. Jun B and Kim D, "Robust face detection using local gradient patterns and evidence accumulation," Pattern Recognition, vol. 45, no. 9, pp. 3304-3316, 2012. https://doi.org/10.1016/j.patcog.2012.02.031
  33. Wen Y, Liu W, and Yang M, et al., "Regularized Robust Coding for Face Recognition," Computer Science, vol. 178, pp. 11-24, 2015.
  34. Martinez A M, "Recognizing imprecisely localized, partially occluded, and expression variant faces from a single sample per class," IEEE Transactions on Pattern Analysis & Machine Intelligence, vol. 24, no. 6, pp. 748-763, 2010.
  35. Tu D N, Tran T, and Phung D, et al. "Learning Parts-based Representations with Nonnegative Restricted Boltzmann Machine," in Proc. of Asian Conference on Machine Learning, pp. 133-148, 2013.
  36. Kobayashi T, "Kernel-based transition probability toward similarity measure for semi-supervised learning," Pattern Recognition, vol. 47, no. 5, pp. 1994-2010, 2014. https://doi.org/10.1016/j.patcog.2013.11.011
  37. Belhumeur P N, Hespanha J P, and Kriegman D J, "Eigenfaces vs. Fisherfaces: Recognition using class specific linear projection," IEEE Transactions on Pattern Analysis & Machine Intelligence, vol. 19, no. 7, pp. 711-720, 1996.
  38. Wan J, Yang M, and Gao Y, et al, "Pairwise Costs in Semisupervised Discriminant Analysis for Face Recognition," IEEE Transactions on Information Forensics & Security, vol. 10, no. 9, pp. 1569-1580, 2014.