Multimedia Tools and Applications

, Volume 78, Issue 2, pp 2181–2197 | Cite as

Facial age feature extraction based on deep sparse representation

  • Haibin LiaoEmail author


In recent years, the research on facial age estimation has attracted more and more interests from the scholars and researchers in the field of psychological, aesthetic, forensic science and computer vision. However, facial age estimation is a challenging work: face age does not suffer from only the influence of intrinsic factors (e.g., genes) but also external factors (e.g., living conditions), so that it is difficult to find accurate features which can describe the change of age. Therefore, this paper proposes a robust face feature extraction method based on dynamic deep sparse representation. Combined with the respective characteristics of Active Appearance Model (AAM), Local Binary Patterns (LBP), Gabor and Bio-Inspired Features (BIF), this method will give sufficient consideration to the thinking way of object recognition of the human, similarity of adjacent ages and the classification principle of signal sparse representation. In addition, in order to reduce the interference of the face identity factor, two factors analysis method is proposed to separate the face identity factor. The experimental results show that the feature extraction method proposed in this paper has strong discrimination and robustness, which outperforms the state-of-the-art age estimation approaches.


Facial age estimation Facial image processing Feature extraction Deep sparse representation 



We want to thank the helpful comments and suggestions from the anonymous reviewers. This work is supported partially by the Hubei Provincial Natural Science Foundation of China (No.2017CFB168), the Hubei Provincial Education Office Science and technology research project youth talent project (No.Q20172805), the Hubei Provincial education science planning project (No.2016GB086), the construction of a special scientific research project for master’s point (No.2018-19GZ050).


  1. 1.
    Ahonen T, Hadid A, Pietikainen M (2006) Face description with localbinary patterns: application to face recognition [J]. PAMI 28(12):2037–2041CrossRefGoogle Scholar
  2. 2.
    Amadasi A, Merusi N, Cattaneo C (2015) How reliable is apparent age at death on cadavers? [J]. Int J Legal Med 129(4):1437–1596Google Scholar
  3. 3.
    Cheema MS, Eweiwi A, Bauckhage C (2014) Human activity recognition by separating style and content [J]. Pattern Recogn Lett 50:130–138CrossRefGoogle Scholar
  4. 4.
    Chen BC, Chen CS, Hsu WH (2014) Cross-age reference coding for age-invariant face recognition and retrieval [C]. ECCV 2014:768–783Google Scholar
  5. 5.
    Chen WY, Qian W, Wu G et al (2015) Three-dimensional human facial morphologies as robust aging markers [J]. Cell Res 25(5):574–587CrossRefGoogle Scholar
  6. 6.
    Chen WY, Qian W, Wu G et al (2015) Three-dimensional human facial morphologies as robust aging markers [J]. Cell Res 25(5):1–14CrossRefGoogle Scholar
  7. 7.
    Choi SE, Lee YJ, Lee SJ et al (2011) Age estimation using a hierarchical classifier based on global and local facial features [J]. Pattern Recogn 44(6):1262–1281zbMATHCrossRefGoogle Scholar
  8. 8.
    Cootes TF, Edwards GJ, Taylor CJ (2001) Active appearance models [J]. PAMI 23(6):681–685CrossRefGoogle Scholar
  9. 9.
    Dayan N (2008) Skin aging handbook: an integrated approach to biochemistry and product development [M]. Andrew William PressGoogle Scholar
  10. 10.
    Elgammal A, Lee C S (2004) Separating style and content on a nonlinear manifold [C].CVPR, p 478–485Google Scholar
  11. 11.
    Fu Y, Huang TS (2008) Human age estimation with regression ondiscriminative aging manifold [J]. IEEE Trans Multimedia 10(4):578–584CrossRefGoogle Scholar
  12. 12.
    Fu Y, Guo G, Huang TS (2010) Age synthesis and estimation via faces: a survey [J]. IEEE Trans Pattern Anal Mach Intell 32(11):1955–1976CrossRefGoogle Scholar
  13. 13.
    Geng Y, Liang RZ, Li W, et al (2016) Learning convolutional neural network to maximize pos@ top performance measure [C]. ESANN 2017 - Proceedings, p 589–594Google Scholar
  14. 14.
    Geng Y, Zhang G, Li W, et al (2017) A novel image tag completion method based on convolutional neural transformation [C]. International Conference on Artificial Neural Networks, p 539–546Google Scholar
  15. 15.
    Guo G, Fu Y, Dyer CR, Huang TS (2008) Image-based human age estimation by manifold learning and locally adjusted robust regression [J]. IEEE Trans Image Process 17(7):1178–1188MathSciNetCrossRefGoogle Scholar
  16. 16.
    Guo G, Fu Y, Huang TS, Dyer CR (2008) Locally adjusted robustregression for human age estimation [C]. ICCV, p 1–6Google Scholar
  17. 17.
    Guo G, Mu G, Fu Y, Huang TS (2009) Human age estimation usingbio-inspired features [C]. CVPR, p 112–119Google Scholar
  18. 18.
    Han H, Otto C, Jain AK (2013) Age estimation from face images: Human vs. machine performance [C]. International Conference on Biometrics, Madrid, SpainGoogle Scholar
  19. 19.
    Iga R, Izumi K, Hayashi H, et al (2003) A gender and age estimation system from face images [C]. In: Proc. SICE Annual Conference, p 756–761Google Scholar
  20. 20.
    KwonYH, da Vitoria Lobo N (1994) Age classification from facial images [C]. CVPR, p 762–767Google Scholar
  21. 21.
    Kwon Y, Lobo N (1999) Age classification from facial images [J]. Comput Vis Image Underst 74(1):1–21CrossRefGoogle Scholar
  22. 22.
    Lanitis A, Taylor CJ, Cootes TF (2002) Toward automatic simulation of aging effects on face images [J]. PAMI 24(4):442–455CrossRefGoogle Scholar
  23. 23.
    Levi G, Hassner T (2015) Age and gender classification using convolutional neural networks [C]. CVPR, p 34–42Google Scholar
  24. 24.
    Liao H, Chen Y, Dai W, Ruan R (2016) Tied factors analysis for high-dimensional image feature extraction and recognition application [J]. Pattern Anal Applic 1–14Google Scholar
  25. 25.
    Mallat S (2012) Group invariant scattering [J]. Commun Pure Appl Math 65(10):1331–1398MathSciNetzbMATHCrossRefGoogle Scholar
  26. 26.
    Martinez A, Du S (2012) A model of the perception of facial expressionsof emotion by humans: research overview and perspectives [J]. J Mach Learn Res 13(1):1589–1608MathSciNetGoogle Scholar
  27. 27.
    O'Toole T, Price TV et al (1999) 3D shape and 2D surface textures of human faces: the role of averages in attractiveness and age [J]. Image Vis Comput 18(1):9–19CrossRefGoogle Scholar
  28. 28.
    Patzelt SBM, Schaible LK, Kohal RJ (2015) Software-based evaluation of human age: a pilot study [J]. J Esthet Restor Dent 27(2):100–106CrossRefGoogle Scholar
  29. 29.
    Ramanathan N, Chellappa R (2006) Modeling age progression in young faces [C]. CVPR, p 387–394Google Scholar
  30. 30.
    Shang L, Chan K-P (2009) Nonparametric discriminant HMM andapplication to facial expression recognition [C]. CVPR, p 2090–2096Google Scholar
  31. 31.
    Tang K, Kamata SI, Hou X et al (2016) Eigen-aging reference coding for cross-age face verification and retrieval [C]. ACCV 2016:389–403Google Scholar
  32. 32.
    Tenenbaum JB, Freeman WT (2000) Separating style and content with bilinear models [J]. Neural Comput 12(6):1247–1283CrossRefGoogle Scholar
  33. 33.
    Wang W, Cui Z, Yan Y, et al (2016) Recurrent Face Aging [C]. CVPR, p 2378–2386Google Scholar
  34. 34.
    Wu F, Jing XY, You X et al (2015) Multi-view low-rank dictionary learning for image classification [J]. Pattern Recogn 50(C):143–154zbMATHGoogle Scholar
  35. 35.
    Yang M, Zhu S, Lv F, Yu K (2011) Correspondence driven adaptation for human profile recognition [C]. CVPR, p 505–512Google Scholar
  36. 36.
    Yang M, Zhang L, Feng X, Zhang D (2011) Fisher discrimination dictionary learning for sparse representation [C]. IEEE International Conference on Computer Vision (ICCV), p 543–550Google Scholar
  37. 37.
    Yi D, Lei Z, Li SZ (2014) Age estimation by multi-scale convolutional network [C]. In Proceedings of 12th Asian Conference on Computer Vision, Singapore, p 1–5Google Scholar
  38. 38.
    Zhang D, Lee WS (2006) Learning to separate text content and style for classification [J]. Lect Notes Comput Sci 4182:79–91CrossRefGoogle Scholar
  39. 39.
    Zhang G, Liang G, Li W, et al (2017) Learning convolutional ranking-score function by query preference regularization [C]. International Conference on Intelligent Data Engineering and Automated Learning, p 1–8Google Scholar
  40. 40.
    Zhou SK, Georgescu B, Zhou XS, Comaniciu D (2005) Image based regression using boosting method [C]. ICCV, p 541–548Google Scholar

Copyright information

© Springer Science+Business Media, LLC, part of Springer Nature 2018

Authors and Affiliations

  1. 1.School of Computer Science and TechnologyHubei University of Science and TechnologyXianningChina

Personalised recommendations