Facial Age Estimation by Conditional Probability Neural Network

  • Chao Yin
  • Xin Geng
Part of the Communications in Computer and Information Science book series (CCIS, volume 321)


A new label distribution learning algorithm for facial age estimation, namely the Conditional Probability Neural Network (CPNN), is proposed in this paper. CPNN is based on a three-layer neural network which takes both the target variable (e.g., the age) and the conditional feature vector (e.g., the facial features) as its inputs, and the output is the conditional probability of the target variable given the feature vector. As a label distribution learning algorithm, CPNN can effectively utilize the neighboring ages while learning the real age. Compared with the existing label distribution learning algorithm IIS-LLD, it does not presume the underlying model as the maximum entropy model, but learns it from the training data. Thus CPNN is able to match the real problem better. Experimental results on the FG-NET database show that CPNN performs remarkably better than all the other eight compared methods.


Label distribution learning neural network age estimation 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. [1]
    Fu, Y., Guo, G.D., Huang, T.S.: Age Synthesis and Estimation via Faces: A Survey. IEEE Transactions on Pattern Analysis and Machine Intelligence 32(11), 1955–1976 (2010)CrossRefGoogle Scholar
  2. [2]
    Selvi, V.T., Vani, K.: Age estimation system using MPCA. In: Proceedings of the International Conference on Recent Trends in Information Technology, Dubai, United Arab Emirates, pp. 1055–1060 (2011)Google Scholar
  3. [3]
    Zhang, Y., Yeung, D.Y.: Multi-task warped Gaussian process for personalized age estimation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Hong Kong, China, pp. 2622–2629 (2011)Google Scholar
  4. [4]
    Geng, X., Zhou, Z.-H., Li, G., Dai, H.: Learning from facial aging patterns for automatic age estimation. In: Proceedings of the ACM International Conference on Multimedia, Santa Barbara, CA, pp. 307–316 (2006)Google Scholar
  5. [5]
    Cootes, T.F., Edwards, G.J., Taylor, C.J.: Active Appearance Models. In: Burkhardt, H., Neumann, B. (eds.) ECCV 1998. LNCS, vol. 1407, pp. 484–498. Springer, Heidelberg (1998)CrossRefGoogle Scholar
  6. [6]
    Guo, G.D., Fu, Y., Dyer, C.R.: Image-Based Human Age Estimation by Manifold Learning and Locally Adjusted Robust Regression. IEEE Transactions on Image Processing 17(7), 1178–1188 (2008)MathSciNetCrossRefGoogle Scholar
  7. [7]
    Lanitis, A., Draganova, C., Christodoulou, C.: Comparing different classifiers for automatic age estimation. IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics 34(1), 621–628 (2004)CrossRefGoogle Scholar
  8. [8]
    Geng, X., Smith-Miles, K.A., Zhou, Z.-H.: Facial Age Estimation by Learing from Label Distributions. In: Proceedings of the 24th AAAI Conference on Artificial Intelligence, Atlanta, GA, pp. 451–456 (2010)Google Scholar
  9. [9]
    Modha, D.S., Fainman, Y.: A learning law for density estimation. IEEE Transactions on Neural Networks 5(3), 519–523 (1994)CrossRefGoogle Scholar
  10. [10]
    Sarajedini, A., Hecht-Nielsen, R., Chau, P.M.: Conditional probability density function estimation with sigmoidal neural networks. IEEE Transactions on Neural Networks 10(2), 231–238 (1999)CrossRefGoogle Scholar
  11. [11]
    Riedmiller, M., Braun, H.: A direct adaptive method for faster backpropagation learning: the RPROP algorithm. In: Proceedings of the IEEE International Conference on Neural Networks, San Francisco, CA, pp. 586–591 (1993)Google Scholar
  12. [12]
    Lanitis, A., Taylor, C.J., Cootes, T.F.: Toward automatic simulation of aging effects on face images. IEEE Transactions on Pattern Analysis and Machine Intelligence 24(4), 442–455 (2002)CrossRefGoogle Scholar
  13. [13]
    Guo, G.D., Mu, G.W.: Human Age Estimation: what is the Influence Across Race and Gender? In: Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, San Francisco, CA, pp. 71–78 (2010)Google Scholar
  14. [14]
    Berger, A., Pietra, S.D., Pietra, V.J.D.: A maximum entropy approach to natural language processing. Computational Linguistics 22(1), 39–71 (1996)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2012

Authors and Affiliations

  • Chao Yin
    • 1
  • Xin Geng
    • 1
  1. 1.School of Computer Science and EngineeringSoutheast UniversityNanjingP.R. China

Personalised recommendations