Skip to main content

Advertisement

SpringerLink
Log in

Human Age Estimation by Considering both the Ordinality and Similarity of Ages

  • Published:
Neural Processing Letters Aims and scope Submit manuscript

Abstract

The age sequence of human beings exhibits two striking characteristics: ordinal in age values and similar in facial appearance of neighboring ages. Although it has been demonstrated that such ordinality especially the neighboring similarity has positive influence on age estimation, existing approaches have yet not simultaneously taken the two types of information into the estimation. In this paper to conduct age estimation with considering both the ordinality and the neighbor similarity which we call soft-age-contribution (SAC), we take the widely used discriminant method LDA and the least squares regression (LS) as the research baseline, respectively. Firstly, we construct inequality-based large margin ordinal constraints and equality-based ordinal regression constraints and, respectively, incorporate them into LDA and LS to develop their respective ordinal counterpart, coined as OrLDA and OrLS. Next, in order to utilize the SAC information, we formulate two types of membership function to depict such neighboring similarity and embed them into OrLDA and OrLS, yielding soft and ordinal variants of LDA and LS, called SAC-OrLDA and SAC-OrLS in which both the ordinality and the neighboring similarity of ages are considered. Finally, through experiments on benchmark aging datasets, we demonstrate the effectiveness of our strategies in utilizing the two types of information to improving age estimation. In addition, we also quantitatively explore the similarity of neighboring ages, finding that generally about neighboring four years are similar in facial appearance to each other.

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
Fig. 8
Fig. 9

Similar content being viewed by others

Notes

  1. It is worthwhile to note that the proposed OrLDA in (4) is essentially different from the KDLOR [27], in both the objective and the form of constraints. In KDLOR, it is assumed that the degree of margins between two neighboring classes is equal, which may be inconsistent with actual classes distributions.

References

  1. Agresti A (2010) Analysis of ordinal categorical data. Wiley, New York

    Book  MATH  Google Scholar 

  2. Alnajar F, Shan C, Gevers T, Geusebroek JM (2012) Learning-based encoding with soft assignment for age estimation under unconstrained imaging conditions. Image Vis Comput 30:946–953

    Article  Google Scholar 

  3. Bathe KJ, Wilson EL (1976) Numerical methods in finite element analysis. Prentice-Hall, Englewood Cliffs

    MATH  Google Scholar 

  4. Boser BE, Guyon IM, Vapnik VN (1992) A training algorithm for optimal margin classifiers. In: Proceedings of the fifth annual workshop on computational learning theory. ACM, Pittsburgh, pp 144–152

  5. Chen K, Gong S, Xiang T, Mary Q, Loy CC, (2013) Cumulative attribute space for age and crowd density estimation. In: IEEE conference on computer vision and pattern recognition CVPR 2013. IEEE, pp 2467–2474

  6. Chu W, Keerthi SS (2005) New approaches to support vector ordinal regression. In: Proceedings of the 22nd international conference on machine learning. ACM, New York, pp 145–152

  7. Cootes TF, Edwards GJ, Taylor CJ (1998) Active appearance models. Computer visionECCV98. Springer, Berlin, pp 484–498

    Google Scholar 

  8. Ding C, Choi J, Tao D, Davis LS (2014) Multi-directional multi-level dual-cross patterns for robust face recognition. arXiv preprint arXiv:1401.5311

  9. Ding C, Tao D, (2015) A comprehensive survey on pose-invariant face recognition. arXiv preprint arXiv:1502.04383

  10. Ding C, Xu C, Tao D (2015) Multi-task pose-invariant face recognition. IEEE Trans Image Process 24:980–993

    Article  MathSciNet  Google Scholar 

  11. Fu Y, Xu Y, Huang, TS (2007) Estimating human age by manifold analysis of face pictures and regression on aging features. In: 2007 IEEE international conference on multimedia and expo. IEEE, pp 1383–1386

  12. Gao F, Ai H (2009) Face age classification on consumer images with gabor feature and fuzzy lda method. Advances in biometrics. Springer, Berlin, pp 132–141

    Chapter  Google Scholar 

  13. Geladi P, Kowalski BR (1986) Partial least-squares regression: a tutorial. Anal chim Acta 185:1–17

    Article  Google Scholar 

  14. Geng X, Yin C, Zhou ZH (2013) Facial age estimation by learning from label distributions. IEEE Trans Pattern Anal Mach Intell 35:2401–2412

    Article  Google Scholar 

  15. Guo G, Fu Y, Dyer CR, Huang TS (2008) Image-based human age estimation by manifold learning and locally adjusted robust regression. IEEE Trans Image Process 17:1178–1188

    Article  MathSciNet  Google Scholar 

  16. Jain AK, Dass SC, Nandakumar K (2004) Soft biometric traits for personal recognition systems. Biometric authentication. Springer, Berlin, pp 731–738

    Chapter  Google Scholar 

  17. Lanitis A, Draganova C, Christodoulou C (2004) Comparing different classifiers for automatic age estimation. IEEE Trans Syst Man Cybern Part B 34:621–628

    Article  Google Scholar 

  18. Lanitis A, Taylor CJ, Cootes TF (2002) Toward automatic simulation of aging effects on face images. IEEE Trans Pattern Anal Mach Intell 24:442–455

    Article  Google Scholar 

  19. Li C, Liu Q, Liu J, Lu H (2012a) Learning distance metric regression for facial age estimation. In: 2012 21st international conference on pattern recognition (ICPR). IEEE, pp 2327–2330

  20. Li C, Liu Q, Liu J, Lu H (2012b) Learning ordinal discriminative features for age estimation. In: 2012 IEEE conference on computer vision and pattern recognition (CVPR). IEEE, pp 2570–2577

  21. Li T, Zhu S, Ogihara M (2006) Using discriminant analysis for multi-class classification: an experimental investigation. Knowl Inf Syst 10:453–472

    Article  Google Scholar 

  22. Liu J, Ma Y, Duan L, Wang F, Liu Y (2014) Hybrid constraint SVR for facial age estimation. Signal Process 94:576–582

    Article  Google Scholar 

  23. Luu K, Ricanek K, Bui TD, Suen CY (2009) Age estimation using active appearance models and support vector machine regression. In: IEEE 3rd international conference on biometrics: theory, applications, and systems, 2009. BTAS’09. IEEE, pp 1–5

  24. Mu G, Guo G, Fu Y, Huang TS (2009) Human age estimation using bio-inspired feature. In: IEEE conference on computer vision and pattern recognition, 2009. CVPR 2009. IEEE, pp 112–119

  25. Fjermestad J, Romano N (2006) Electronic customer relationship management, vol 3. ME Sharpe

  26. Sai PK, Wang JG, Teoh EK (2015) Facial age range estimation with extreme learning machines. Neurocomputing 149:364–372

    Article  Google Scholar 

  27. Sun BY, Li J, Wu DD, Zhang XM, Li WB (2010) Kernel discriminant learning for ordinal regression. IEEE Trans Knowl Data Eng 22:906–910

    Article  Google Scholar 

  28. Ueki K, Hayashida T, Kobayashi T, (2006) Subspace-based age-group classification using facial images under various lighting conditions. In: 7th international conference on automatic face and gesture recognition, 2006. FGR 2006. IEEE, p 6

  29. Vapnik VN (1998) Statistical learning theory. Wiley, New York

    MATH  Google Scholar 

  30. Zhang T, Zhou ZH (2013) Large margin distribution machine. arXiv preprint arXiv:1311.0989

Download references

Acknowledgments

This work was partially supported by the National Natural Science Foundation of China under Grants \(61472186\), \(61375057\) and \(61300154\), Natural Science Foundation of Jiangsu Province of China under Grant \(BK20131298\), Funding of Jiangsu Innovation Program for Graduate Education under Grant \(CXLX13\_159\), and the Fundamental Research Funds for the Central Universities. In addition, we would like to express our gratitude to Prof. Songcan Chen (now with the College of Computer Science and Technology, Nanjing University of Aeronautics and Astronautics, Nanjing, China) for his valuable advice on building the related models in this work.

Author information

Authors and Affiliations

  1. College of Computer Science and Technology, Nanjing University of Aeronautics and Astronautics, Nanjing, 210016, China

    Qing Tian

  2. School of Computer Science and Engineering, Southeast University, Nanjing, 210096, China

    Hui Xue

  3. School of Mathematical Sciences, Liaocheng University, Liaocheng, 252059, China

    Lishan Qiao

Authors
  1. Qing Tian
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Hui Xue
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Lishan Qiao
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Lishan Qiao.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Tian, Q., Xue, H. & Qiao, L. Human Age Estimation by Considering both the Ordinality and Similarity of Ages. Neural Process Lett 43, 505–521 (2016). https://doi.org/10.1007/s11063-015-9423-8

Download citation

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11063-015-9423-8

Keywords

Search

Navigation