Encode Locally, Discriminate Holistically: A Method Extracting Multi-resolution Features for Facial Age Estimation

  • Shenglan Ben
  • Jie Ma
  • Zhong Jin
  • Jingyu Yang
Part of the Communications in Computer and Information Science book series (CCIS, volume 321)


To combine the global and local aging information of face images, this paper proposes a feature extraction method which can extract multi-resolution discriminative local features in a holistic way for age estimation. By using 2DPCA on the left side of the block matrixes, the face images are firstly transformed into lower dimensional representation matrixes whose rows can be seen as block-wise image representations in different resolutions. Discriminate features are then extracted holistically for each of the resolutions by viewing each row as a sample. Based on the weak estimator on each of the resolutions, an ensemble is finally constructed to perform the age estimation task. Experimental results confirm the reliability of the proposed method compared with related methods.


Age Estimation Feature Extraction Estimator Ensemble 2DPCA LDA 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Takimoto, H., Mitsukura, Y., Fukumi, M., Akamatsu, N.: Robust Gender and Age Estimation Under Varying Face Pose. Electronics and Communications in Japan 91(7), 32–40 (2008)CrossRefGoogle Scholar
  2. 2.
    Hayashi, J., Yasukata, M., Ito, H., et al.: Age and Gender Estimation Based on Facial Image Analysis. In: Palade, V., Howlett, R.J., Jain, L. (eds.) KES 2003. LNCS, vol. 2774, pp. 1611–3349. Springer, Heidelberg (2003)Google Scholar
  3. 3.
    Gao, F., Ai, H.Z.: Face Age Classification on Consumer Images with Gabor Feature and Fuzzy LDA Method. In: Tistarelli, M., Nixon, M.S. (eds.) ICB 2009. LNCS, vol. 5558, pp. 132–141. Springer, Heidelberg (2009)CrossRefGoogle Scholar
  4. 4.
    Günay, A., Nabiyev, V.: Automatic Age Classification with LBP. In: Proc. International Symposium on Computer and Information Sciences (2008)Google Scholar
  5. 5.
    Yan, S., Liu, M., Huang, T.S.: Extracting Age Information form Local Spatially Flexible Patches. In: Proc. IEEE Conf. on ICASSP, pp. 737–740 (2008)Google Scholar
  6. 6.
    Serrre, T., Wolf, L., Bileschi, S., Riesenhuber, M., Poggio, T.: Robust Object Recognition with Cortex-Like Mechanisms. IEEE Trans. Pattern Anal. Mach. Intell. 29(3), 411–426 (2007)CrossRefGoogle Scholar
  7. 7.
    Guo, G., Mu, G., Yun, F., Huang, T.S.: Human Age Estimation Using Bio-Inspired Features. In: Proc. IEEE Conf. on CVPR, pp. 112–119 (2009)Google Scholar
  8. 8.
    Cootes, T., Edwards, G., Taylor, C.: Active Appearance Models. IEEE Trans. on Pattern Anal. Mach. Intell. 23(6), 681–685 (2001)CrossRefGoogle Scholar
  9. 9.
    Lanitis, A., Taylor, C., Cootes, T.: Toward Automatic Simulation of Aging Effects on Face Images. IEEE Trans. on Pattern Anal. Mach. Intell. 24(4), 442–455 (2002)CrossRefGoogle Scholar
  10. 10.
    Geng, X., Zhou, Z.H., Smith-Miles, K.: Automatic Age Estimation Based on Facial Aging Patterns. EEE Trans. on Pattern Anal. Mach. Intell. 29(12), 2234–2240 (2007)CrossRefGoogle Scholar
  11. 11.
    Wang, J.G., Sung, E., Yau, W.Y.: Active Learning for Solving the Incomplete Data Problem in Facial Age Classification by the Furthest Nearest-Neighbor Criterion. IEEE Trans. Image Processing. 20(7), 2049–2062 (2011)MathSciNetCrossRefGoogle Scholar
  12. 12.
    Wang, L.W., Wang, X., Feng, J.F.: On Image Matrix based Feature Extraction Algorithms. IEEE Trans. Syst. Man. Cybern. Part B: Cybern. 36, 194–197 (2006)CrossRefGoogle Scholar
  13. 13.
    Sinha, P., Balas, B., Ostrovsky, Y., Russel, R.: Face Recognition by Humans: Nineteen Results all Computer Vision Researchers Should Know About. Proceedings of the IEEE 94, 1948–1962 (2006)CrossRefGoogle Scholar
  14. 14.
    Cootes, T., Lanitis, A.: The FG-NET Aging Database,
  15. 15.
    Ye, J.: Generalized low rank approximations of matrices. Mach. Learn. 61, 167–191 (2005)zbMATHCrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2012

Authors and Affiliations

  • Shenglan Ben
    • 1
  • Jie Ma
    • 2
  • Zhong Jin
    • 1
  • Jingyu Yang
    • 1
  1. 1.NanJing University of Science and TechnologyChina
  2. 2.ZTE CorporationNanjingChina

Personalised recommendations