Abstract
Human facial age estimation has attracted much attention in the field of computer vision in recent decades, due to its potential applications in human–computer interaction and electronic customer relationship management. However, the insufficiency of labeled facial images has made age estimation a challenging problem. Being aware of this, we focus on learning the ordinal relationships among different age labels from limited training samples. To exploit the intrinsic property of ordinal relationships, the learning problem is formulated as a structured sparse multi-class classification model regularized by the structured sparsity. The structured sparse regularization encodes the ordinal relationships among different age labels, and ensures that the samples with similar age labels are close to each other in the feature space. In addition, by aggregating the prediction functions for different age labels into a matrix W, we introduce the grouped sparsity which constrains the matrix W to share a common subspace. The smoothing proximal gradient (SPG) method is employed to optimize the proposed model since the objective function is convex and non-smooth with respect to variable W. Additionally, we conduct experiments on two publicly available facial image datasets, the FG-NET and the MORPH-II, and the empirical results have demonstrated the effectiveness of the proposed method against the state-of-the-arts.





Similar content being viewed by others
References
Beck, A., Teboulle, M.: A fast iterative shrinkage-thresholding algorithm for linear inverse problems. SIAM J. Imaging Sci. 2(1), 183–202 (2009)
Chang, K.Y., Chen, C.S.: A learning framework for age rank estimation based on face images with scattering transform. IEEE Trans. Image Process. 24(3), 785–798 (2015)
Chang, K.Y., Chen, C.S., Hung, Y.P.: A ranking approach for human ages estimation based on face images. In: ICPR, pp. 3396–3399. IEEE Computer Society, New York (2010)
Chang, K.Y., Chen, C.S., Hung, Y.P.: Ordinal hyperplanes ranker with cost sensitivities for age estimation. In: CVPR, pp. 585–592. IEEE Computer Society, New York (2011)
Chao, W.L., Liu, J.Z., Ding, J.J.: Facial age estimation based on label-sensitive learning and age-oriented regression. Pattern Recognit. 46(3), 628–641 (2013)
Chen, K., Gong, S., Xiang, T., Loy, C.C.: Cumulative attribute space for age and crowd density estimation. In: CVPR, pp. 2467–2474. IEEE Computer Society, New York (2013)
Chen, X., Lin, Q., Kim, S., Carbonell, J.G., Xing, E.P.: Smoothing proximal gradient method for general structured sparse learning. arXiv:1202.3708 (2012)
Cootes, T.F., Edwards, G.J., Taylor, C.J.: Active appearance models. IEEE Trans. Pattern Anal. Mach. Intell. 23(6), 681–685 (2001)
Fu, Y., Guo, G., Huang, T.S.: Age synthesis and estimation via faces: a survey. IEEE Trans. Pattern Anal. Mach. Intell. 32(11), 1955–1976 (2010)
Fu, Y., Huang, T.S.: Human age estimation with regression on discriminative aging manifold. IEEE Trans. Multimed. 10(4), 578–584 (2008)
Geng, X., Yin, C., Zhou, Z.H.: Facial age estimation by learning from label distributions. IEEE Trans. Pattern Anal. Mach. Intell. 35(10), 2401–2412 (2013)
Geng, X., Zhou, Z.H., Smith-Miles, K.: Automatic age estimation based on facial aging patterns. IEEE Trans. Pattern Anal. Mach. Intell. 29(12), 2234–2240 (2007)
Geng, X., Zhou, Z.H., Zhang, Y., Li, G., Dai, H.: Learning from facial aging patterns for automatic age estimation. In: ACM Multimedia, pp. 307–316. ACM, New York (2006)
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)
Guo, G., Fu, Y., Huang, T.S., Dyer, C.R.: Locally adjusted robust regression for human age estimation. In: IEEE Workshop on Applications of Computer Vision, pp. 1–6 (2008)
Guo, G., Mu, G.: Simultaneous dimensionality reduction and human age estimation via kernel partial least squares regression. In: CVPR, pp. 657–664. IEEE Computer Society, New York (2011)
Guo, G., Mu, G., Fu, Y., Huang, T.S.: Human age estimation using bio-inspired features. In: CVPR, pp. 112–119. IEEE Computer Society, New York (2009)
Guo, G., Zhang, C.: A study on cross-population age estimation. In: CVPR, pp. 4257–4263. IEEE Computer Society, New York (2014)
Han, L., Zhang, Y.: Learning multi-level task groups in multi-task learning. In: AAAI, pp. 2638–2644. AAAI Press, New York (2015)
Jr., K.R., Tesafaye, T.: Morph: a longitudinal image database of normal adult age-progression. pp. 341–345. IEEE Computer Society, New York (2006)
Khryashchev, V.V., Ganin, A., Stepanova, O., Lebedev, A.: Age estimation from face images: challenging problem for audience measurement systems, pp. 31–37. IEEE, New York (2014)
Lai, D., Chen, Y., Luo, X., Du, J., Wang, T.: Age estimation with dynamic age range. In: Multimedia Tools and Applications, pp. 1–23 (2016)
Lanitis, A., Draganova, C., Christodoulou, C.: Comparing different classifiers for automatic age estimation. IEEE Trans. Syst. Man Cybern. 34, 621–628 (2004)
Li, C., Liu, Q., Liu, J., Lu, H.: Learning distance metric regression for facial age estimation. In: ICPR, pp. 2327–2330. IEEE Computer Society, New York (2012)
Li, C., Liu, Q., Liu, J., Lu, H.: Learning ordinal discriminative features for age estimation. In: CVPR, pp. 2570–2577. IEEE Computer Society, New York (2012)
Liu, G., Lin, Z., Yan, S., Sun, J., Yu, Y., Ma, Y.: Robust recovery of subspace structures by low-rank representation. IEEE Trans. Pattern Anal. Mach. Intell. 35(1), 171–184 (2013)
Song, Z., Ni, B., Guo, D., Sim, T., Yan, S.: Learning universal multi-view age estimator using video context. In: ICCV, pp. 241–248 (2011)
Feng, S., Lang, C., Feng, J., Wang, T., Luo, J.: Human facial age estimation by cost-sensitive label ranking and trace norm regularization. IEEE Trans. Multimed. 19(1), 136–148 (2017)
Tian, Q., Xue, H., Qiao, L.: Human age estimation by considering both the ordinality and similarity of ages. Neural Process. Lett. 43(2), 505–521 (2016)
Wang, S., Tao, T., Yang, J.: The fg-net aging database. http://www.fgnet.rsunit.com/ (2009)
Yang, Z., Ai, H.: Demographic classification with local binary patterns. In: ICB, vol. 4642, pp. 464–473. Springer, New York (2007)
Zhou, Q., Zhao, Q.: Flexible clustered multi-task learning by learning representative tasks. IEEE Trans. Pattern Anal. Mach. Intell. 38(2), 266–278 (2016)
Acknowledgements
This work is supported by the National Nature Science Foundation of China (Nos. 61300071, 61272352, 61370060, 61372148, 61472028 and 61502026), Beijing Natural Science Foundation (Nos. 4142045, 4162048 and 4163075).
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Dong, Y., Lang, C. & Feng, S. General structured sparse learning for human facial age estimation. Multimedia Systems 25, 49–57 (2019). https://doi.org/10.1007/s00530-017-0534-0
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00530-017-0534-0