Skip to main content
SpringerLink
Log in

Learning to pool high-level features for face representation

  • Original Article
  • Published:
The Visual Computer Aims and scope Submit manuscript

Abstract

The available face descriptors are always generated by a hand-designed pooling scheme or without a pooling process. We propose to learn a pooling scheme for high-level features. First, we obtain the local features on the densely sampled points on a face image. Then, a weighted-sum pooling is used to obtain the high-level feature of a block of this face image. By learning the pooling weights, the structure information of local features is integrated into the high-level feature of the block. At the same time, a linear transformation is learned to reduce the dimension of this high-level feature. Our main contribution is the method of learning the pooling scheme, which can capture the structure information between the local features in a block. This structure information includes the facial structures and contours. The experiments on multiple face datasets confirm the efficiency and effectiveness of our method.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7

Similar content being viewed by others

References

  1. Arigbabu, O.A., Ahmad, S.M.S., Adan, W.A.W., Yussof, S.: Recent advances in facial soft biometrics. In: The Visual Computer (2014). doi:10.1007/s00371-014-0990-x

  2. Tan, X., Triggs, B.: Enhanced local texture feature sets for face recognition under difficult lighting conditions. TIP 19(6), 1635–1650 (2010)

    MathSciNet  Google Scholar 

  3. Zhang, W., Shan, S., Gao, W., Chen, X., Zhang, H.: Local Gabor binary pattern histogram sequence (LGBPHS): a novel non-statistical model for face representation and recognition. In: ICCV (2005)

  4. Seo, H., Milanfar, P.: Face verification using the LARK representation. TIFS 6(4), 1275–1286 (2011)

    Google Scholar 

  5. Xu, P., Ye, M., Li, X., Pei, L., Jiao, P.: Object detection using voting spaces trained by few samples. Opt. Eng. 52(9), 093105–093105 (2013)

    Article  Google Scholar 

  6. Wolf, L., Hassner, T., Taigman, Y.: Similarity scores based on background samples. In: ACCV (2009)

  7. Vu, N., Caplier, A.: Enhanced patterns of oriented edge magnitudes for face recognition and image matching. TIP 21(3), 1352–1365 (2012)

    MathSciNet  Google Scholar 

  8. Singh, C., Walia, E., Mittal, N.: Robust two-stage face recognition approach using global and local features. Vis. Comput. 28(11), 1085–1098 (2012)

    Article  Google Scholar 

  9. Cao, Z., Yin, Q., Tang, X., Sun, J.: Face recognition with learning-based descriptor. In: CVPR, pp. 2707–2714 (2010)

  10. Huang, G.B., Lee, H., Learned-Miller, E.: Learning hierarchical representations for face verification with convolutional deep belief networks. In: CVPR, pp. 2518–2525 (2012)

  11. Zhu, Z., Luo, P., Wang, X., Tang, X.: Deep learning identity preserving face space. In: ICCV, pp. 113–120 (2013)

  12. Cui, Z., Shan, S., Chen, X., Zhang, L.: Sparsely encoded local descriptor for face recognition. In: FG, pp. 149–154 (2011)

  13. Cui, Z., Wen, L., Xu, D., Shan, S., Chen, X.: Fusing robust face region descriptors via multiple metric learning for face recognition in the wild. In: CVPR, pp. 3554–3561 (2013)

  14. Lu, C., Min, H., Gui, J., Zhu, L., Lei, Y.: Face recognition via weighted sparse representation. J. Vis. Commun. Image Represent. 24, 111–116 (2013)

    Article  Google Scholar 

  15. Simonyan, K., Parkhi, O.M., Vedaldi, A., Zisserman, A.: Fisher vector faces in the wild. In: BMVC, pp. 1–12 (2013)

  16. Pinto, N., Cox, D.: Beyond simple features: a large-scale feature search approach to unconstrained face recognition. In: FG, pp. 8–15 (2011)

  17. Lei, Z., Pietikäinen, M., Li, S.Z.: Learn discriminant face descriptor. PAMI 36(2), 289–302 (2014)

  18. Boureau, Y.L., Ponce, J., LeCun, Y.: A theoretical analysis of feature pooling in visual recognition. In: ICML, pp. 111–118 (2010)

  19. Yang, J., Yu, K., Gong, Y., Huang, T.: Linear spatial pyramid matching using sparse coding for image classification. In: CVPR, pp. 1794–1801 (2009)

  20. LeCun, Y., Bottou, L., Bengio, Y., Haffner, P.: Gradient based learning applied to document recognition. Proc. IEEE 86(11), 2278–2324 (1998)

    Article  Google Scholar 

  21. Murray, N., Perronnin, F.: Generalized max pooling. In: CVPR (2014)

  22. De Campos, T., Csurka, G., Perronnin, F.: Images as sets of locally weighted features. CVIU 116(1), 68–85 (2012)

    Google Scholar 

  23. Xu, C., Vasconcelos, N.: Learning receptive fields for pooling from tensors of feature response. In: CVPR (2014)

  24. Lin, D., Lu, C., Liao, R., Jia, J.: Learning important spatial pooling regions for scene classification. In: CVPR (2014)

  25. Leey, C., Bhardwaj, A., Di, W., Jagadeesh, V., Piramuthu, R.: Region-based discriminative feature pooling for scene text recognition. In: CVPR (2014)

  26. Hoyer, P.O.: Non-negative sparse coding. In: NNSP, pp. 557–565 (2002)

  27. Izenman, A.J.: Modern Multivariate Statistical Techniques, pp. 237–280. Springer, New York (2008)

  28. Wang, H., Ye, M., Yang, S.: Shadow compensation and illumination normalization of face image. Mach. Vis. Appl. 24(6), 1121–1131 (2013)

    Article  Google Scholar 

  29. Efron, B., Hastie, T., Johnstone, I., Tibshirani, R.: Least angle regression. Ann. Stat. 32(2), 407–499 (2004)

    Article  MathSciNet  MATH  Google Scholar 

  30. Elkan, C.: Using the triangle inequality to accelerate k-means. In: ICML, pp. 147–153 (2003)

  31. Vanderbei, R.J., Shanno, D.F.: An interior-point algorithm for nonconvex nonlinear programming. Comput. Optim. Appl. 13(1–3), 231–252 (1999)

    Article  MathSciNet  MATH  Google Scholar 

  32. Nocedal, J., Wright, S.J.: Numerical Optimization, pp. 274–278. Springer, New York (2006)

  33. Carreira, J., Caseiro, R., Batista, J., Sminchisescu, C.: Semantic segmentation with second-order pooling. In: ECCV, pp. 430–443 (2012)

  34. Phillips, P.J., Flynn, P.J., Scruggs, T., Bowyer, K.W.: Overview of the face recognition grand challenge. In: Proc. IEEE Computer Society Conference on CVPR, pp. 947–954. San Diego, CA, USA (2005)

  35. Fan, R., Chang, K., Hsieh, C., Wang, X., Lin, C.J.: LIBLINEAR: a library for large linear classification. JMLR 9, 1871–1874 (2008)

    MATH  Google Scholar 

  36. Jolliffe, T.: Principal Component Analysis, pp. 11–17, Wiley Online Library (2005)

  37. Huang, G.B., Ramesh, M., Berg, T., Learned-Miller, E.: Labeled faces in the wild: a database for studying face recognition in unconstrained environments. In: University of Massachusetts, Amherst (2007)

  38. Kumar, N., Berg, A.C., Belhumeur, P.N., Nayar, S.K.: Attribute and simile classifiers for face verification. In: ICCV, pp. 365–372 (2009)

  39. Xiong, X., De la Torre, F.: Supervised descent method and its applications to face alignment. In: CVPR, pp. 532–539 (2013)

  40. Davis, J.V., Kulis, B., Sra, P., Dhillon, I.S.: Information-theoretic metric learning. In: ICML, pp. 209–216 (2007)

  41. Huang, R., Li, T., Ye, M., Dou, Y.: Unconstrained face verification by optimally organizing multiple classifiers. Int. J. Control Autom. Syst. 12(4), 833–842 (2014)

    Article  Google Scholar 

Download references

Acknowledgments

This work was supported in part by the National Natural Science Foundation of China (61375038) and the Fundamental Research Funds for the Central Universities (XDJK2013C122). This work was also partly supported by Engineering and Technological Research Center of Intelligent Instrument and Controlling Device of ChongQing.

Author information

Authors and Affiliations

  1. School of Computer Science and Engineering, Center for Robotics, Key Laboratory for NeuroInformation of Ministry of Education, University of Electronic Science and Technology of China, Chengdu, 611731, People’s Republic of China

    Renjie Huang, Mao Ye, Pei Xu, Tao Li & Yumin Dou

  2. School of Computer and Information Science, Southwest University, Chongqing, 400715, People’s Republic of China

    Renjie Huang

  3. Department of Information Engineering, HeNan Radio and Television University, Zhengzhou, 450046, People’s Republic of China

    Tao Li

Authors
  1. Renjie Huang
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Mao Ye
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Pei Xu
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Tao Li
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Yumin Dou
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Mao Ye.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Huang, R., Ye, M., Xu, P. et al. Learning to pool high-level features for face representation. Vis Comput 31, 1683–1695 (2015). https://doi.org/10.1007/s00371-014-1049-8

Download citation

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00371-014-1049-8

Keywords

Search

Navigation