Adaptive Quotient Image with 3D Generic Elastic Models for Pose and Illumination Invariant Face Recognition

  • Zhongjun Wu
  • Weihong Deng
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 9428)


Large pose and illumination variations are very challenging for face recognition. In this paper, we address this challenge by combining an Adaptive Quotient Image method with 3D Generic Elastic Models (AQI-GEM). Frontal, neutral light face is re-rendered virtually under varying illumination conditions by AQI. Nearly accurate 3D models are constructed from each re-rendered image by GEM so as to virtually synthesize images under varying poses and illumination conditions. Pose-specific metrics are learnt for recognition. Experiments on MultiPIE demonstrate that it outperforms state-of-the-art face recognition methods, with much simpler parameter tuning, and much less training data.


Face recognition Pose and illumination Face re-rendering 3D face construction 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Heo, J.: Generic Elastic Models for 2D Pose Synthesis and Face Recognition. Ph.D thesis, Department of Electrical and Computer Engineering, Carnegie Mellon University (2009)Google Scholar
  2. 2.
    Prabhu, U., Heo, J., Savvides, M.: Unconstrained pose-invariant face recognition using 3d generic elastic models. J. IEEE Transactions on PAMI 33(10), 1952–1961 (2011)CrossRefGoogle Scholar
  3. 3.
    Heo, J., Savvides, M.: Gender and ethnicity specific generic elastic models from a single 2d image for novel 2d pose face synthesis and recognition. J. IEEE Transactions on PAMI 34(12), 2341–2350 (2012)CrossRefGoogle Scholar
  4. 4.
    Moeini, A., Moeini, H.: Real-World and Rapid Face Recognition Toward Pose and Expression Variations via Feature Library Matrix. J. Information Forensics and Security 10(5), 969–984 (2015)CrossRefGoogle Scholar
  5. 5.
    Shashua, A., Riklin-Raviv, T.: The quotient image: Class-based re-rendering and recognition with varying illuminations. J. IEEE Transactions on PAMI 23(2), 129–139 (2001)CrossRefGoogle Scholar
  6. 6.
    Gross, R., Matthews, I., Cohn, J., et al.: Multi-pie. J. Image and Vision Computing 28(5), 807–813 (2010). ElsevierCrossRefGoogle Scholar
  7. 7.
    Milborrow, S., Nicolls, F.: Active shape models with sift descriptors and MARS. J. VISAPP 1(2), 5 (2014)Google Scholar
  8. 8.
    Xiong, X. De la Torre, F.: Supervised descent method and its applications to face alignment. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 532–539 (2013)Google Scholar
  9. 9.
    Taigman, Y., Yang, M., Ranzato, M.A., et al.: Deepface: Closing the gap to human-level performance in face verification. In: 2014 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1701–1708 (2014)Google Scholar
  10. 10.
    Hastie, T., Tibshirani, R., Friedman, J., et al.: The elements of statistical learning. Springer, New York (2009)CrossRefzbMATHGoogle Scholar
  11. 11.
    Li, A., Shan, S., Gao, W.: Coupled bias-variance tradeoff for cross-pose face recognition. J. Image Processing 21(1), 305–315 (2012)MathSciNetCrossRefGoogle Scholar
  12. 12.
    Zhu, Z., Luo, P., Wang, X., et al.: Deep learning identity-preserving face space. In: 2013 IEEE International Conference on Computer Vision (ICCV), pp. 113–120 (2013)Google Scholar
  13. 13.
    Jung, J.Y.H., Yoo, B.I., Choi, C., et al.: Rotating Your Face Using Multi-task Deep Neural Network (2015)Google Scholar

Copyright information

© Springer International Publishing Switzerland 2015

Authors and Affiliations

  1. 1.School of Information and Communication EngineeringBeijing University of Posts and TelecommunicationsBeijingChina

Personalised recommendations