Deep Learning Features for Face Age Estimation: Better Than Human?

  • Krzysztof KotowskiEmail author
  • Katarzyna Stapor
Conference paper
Part of the Communications in Computer and Information Science book series (CCIS, volume 928)


Deep convolutional neural networks have the ability to infer highly representative features from data. We decided to use this power for the purpose of estimating the human face age from a single colour image. We trained the Support Vector Machine regression model on raw feature vectors from the FaceNet deep neural network pretrained for face recognition. Our proposed method is a simple but effective FaceNet extension which does not need large scale data. In order to measure the accuracy of our approach, we proposed a test procedure on the FACES database for which we achieved the mean absolute error of 5.18 and the mean error of 0.09 years. Then, we conducted an experiment employing 78 students and showed that our method outperforms human for faces in the regular upright orientation. For vertically inverted faces, we reported an age underestimation trend in responses of students and our method.


Deep neural networks Age estimation Face analysis 


  1. 1.
    Bartlett, J., Searcy, J.: Inversion and configuration of faces. Cogn. Psychol. 25(3), 281–316 (1993)CrossRefGoogle Scholar
  2. 2.
    Ciresan, D., Meier, U., Masci, J., Schmidhuber, J.: Multi-column deep neural network for traffic sign classification. Neural Netw. 32, 333–338 (2012). selected Papers from IJCNN 2011CrossRefGoogle Scholar
  3. 3.
    Cloutier, J., Freeman, J.B., Ambady, N.: Investigating the early stages of person perception: the asymmetry of social categorization by sex vs. age. PLoS One 9(1), e84677 (2014)CrossRefGoogle Scholar
  4. 4.
    Costello, P.: The perception of age in human faces: upright and inverted results. J. Vis. 7(9), 512 (2007)Google Scholar
  5. 5.
    Craig, B.M., Lipp, O.V.: Facial age cues and emotional expression interact asymmetrically: age cues moderate emotion categorisation. Cogn. Emot. 9931(April), 1–13 (2017)Google Scholar
  6. 6.
    Dehon, H., Brédart, S.: An ‘other-race’ effect in age estimation from faces. Perception 30(9), 1107–1113 (2001)CrossRefGoogle Scholar
  7. 7.
    Ebner, N.C., Riediger, M., Lindenberger, U.: FACES - a database of facial expressions in young, middle-aged, and older women and men: development and validation. Behav. Res. Methods 42(1), 351–362 (2010)CrossRefGoogle Scholar
  8. 8.
    Eimer, M.: The face-sensitive N170 component of the event-related brain potential. Oxf. Handb. Face Percept. 28, 329–344 (2012)Google Scholar
  9. 9.
    Feusner, J.D., et al.: Inverted face processing in body dysmorphic disorder. J. Psychiatr. Res. 44(15), 1088–1094 (2012)CrossRefGoogle Scholar
  10. 10.
    Fitousi, D.: Binding sex, age, and race in unfamiliar faces: the formation of face files. J. Exp. Soc. Psychol. 71, 1–15 (2017)CrossRefGoogle Scholar
  11. 11.
    Guo, G., Fu, Y., Dyer, C.R., Huang, T.S.: Image-based human age estimation by manifold learning and locally adjusted robust regression. IEEE Trans. Image Process. 17(7), 1178–1188 (2008)MathSciNetCrossRefGoogle Scholar
  12. 12.
    Guo, G., Mu, G., Fu, Y., Dyer, C.R., Huang, T.S.: A study on automatic age estimation using a large database. In: 2009 IEEE 12th International Conference on Computer Vision, pp. 1986–1991 (2009)Google Scholar
  13. 13.
    Guo, Y., Zhang, L., Hu, Y., He, X., Gao, J.: MS-Celeb-1M: a dataset and benchmark for large scale face recognition. CoRR. vol. abs/1607.0 (2016)Google Scholar
  14. 14.
    Han, H., Otto, C., Liu, X., Jain, A.K.: Demographic estimation from face images: human vs. machine performance. IEEE Trans. Pattern Anal. Mach. Intell. 37(6), 1148–1161 (2015)CrossRefGoogle Scholar
  15. 15.
    Huang, G.B., Ramesh, M., Berg, T., Learned-Miller, E.: Labeled faces in the wild: a database for studying face recognition in unconstrained environments. Technical report 1, 07–49, University of Massachusetts Amherst (2007)Google Scholar
  16. 16.
    Kwon, Y.H., da Vitoria Lobo, N.: Age classification from facial images. In: 1994 Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, pp. 762–767, June 1994Google Scholar
  17. 17.
    Liu, X., et al.: AgeNet : deeply learned regressor and classifier for robust apparent age estimation. In: 2015 IEEE International Conference on Computer Vision Workshop, pp. 258–266 (2015)Google Scholar
  18. 18.
    Özbulak, G., Aytar, Y., Ekenel, H.K.: How transferable are CNN-based features for age and gender classification? In: Proceedings - Series of the Gesellschaft fur Informatik (GI). Lecture Notes in Informatics (LNI), vol. P-260, no. 113 (2016)Google Scholar
  19. 19.
    Panis, G., et al.: Overview of research on facial ageing using the FG-NET ageing database. IET Biom. 5(2), 37–46 (2016)CrossRefGoogle Scholar
  20. 20.
    Psalta, L., Young, A.W., Thompson, P., Andrews, T.J.: Orientation-sensitivity to facial features explains the Thatcher illusion. J. Vis. 14(12), 9–9 (2014)CrossRefGoogle Scholar
  21. 21.
    Quartz, S.R., Sejnowski, T.J.: The neural basis of cognitive development: a constructivist manifesto. Behav. Brain Sci. 20(4), 537–556 (1997)Google Scholar
  22. 22.
    Rothe, R., Timofte, R., Gool, L.V.: DEX: deep EXpectation of apparent age from a single image. In: 2015 IEEE International Conference on Computer Vision Workshop (ICCVW), pp. 252–257 (2015)Google Scholar
  23. 23.
    Russakovsky, O., et al.: ImageNet large scale visual recognition challenge. Int. J. Comput. Vis. (IJCV) 115(3), 211–252 (2015)MathSciNetCrossRefGoogle Scholar
  24. 24.
    Saikauskiene, A., Daugirdiene, A.: Face recognition peculiarities of different age people in a Lithuanian sample. Int. J. Psychol.: Biopsychosoc. Approach 17, 7–23 (2015)Google Scholar
  25. 25.
    Schroff, F., Kalenichenko, D., Philbin, J.: FaceNet: a unified embedding for face recognition and clustering. In: Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 07–12 June, pp. 815–823 (2015)Google Scholar
  26. 26.
    Schwaninger, A., Carbon, C.C., Leder, H.: Expert Face Processing: Specialization and Constraints. The Development of Face Processing, pp. 81–97 (2003)Google Scholar
  27. 27.
    Short, L.A., Mondloch, C.J.: Aging faces and aging perceivers: young and older adults are less sensitive to deviations from normality in older than in young adult faces. Perception 42(8), 795–812 (2013)CrossRefGoogle Scholar
  28. 28.
    Szegedy, C., Ioffe, S., Vanhoucke, V., Alemi, A.: Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning (2016)Google Scholar
  29. 29.
    Thompson, P.: Margaret Thatcher: a new illusion. Perception 9(4), 483–484 (1980)CrossRefGoogle Scholar
  30. 30.
    Voelkle, M.C., Ebner, N.C., Lindenberger, U., Riediger, M.: Let me guess how old you are: effects of age, gender, and facial expression on perceptions of age. Psychol. Aging 27(2), 265–277 (2012)CrossRefGoogle Scholar
  31. 31.
    Wen, Y., Zhang, K., Li, Z., Qiao, Y.: A discriminative feature learning approach for deep face recognition. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9911, pp. 499–515. Springer, Cham (2016). Scholar
  32. 32.
    van de Wolfshaar, J., Karaaba, M.F., Wiering, M.A.: Deep convolutional neural networks and support vector machines for gender recognition. In: IEEE Symposium Series on Computational Intelligence, pp. 188–195 (2015)Google Scholar
  33. 33.
    Zhang, K., Zhang, Z., Li, Z., Qiao, Y.: Joint face detection and alignment using multi-task cascaded convolutional networks. IEEE Sig. Process. Lett. PP(99), 1–5 (2016)Google Scholar
  34. 34.
    Zhao, M., Hayward, W.G.: Holistic processing underlies gender judgments of faces. Atten. Percept. Psychophys. 72(3), 591–596 (2010)CrossRefGoogle Scholar
  35. 35.
    Zhu, Y., Li, Y., Mu, G., Guo, G.: A study on apparent age estimation. In: 2015 IEEE International Conference on Computer Vision Workshop (ICCVW), pp. 267–273, December 2015Google Scholar
  36. 36.
    Zhuang, X., Zhou, X., Hasegawa-Johnson, M., Huang, T.: Face age estimation using patch-based hidden Markov model supervectors. In: 19th International Conference on Pattern Recognition, pp. 1–4 (2008)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2018

Authors and Affiliations

  1. 1.Institute of InformaticsSilesian University of TechnologyGliwicePoland

Personalised recommendations