Age Estimation Using 3D Shape of the Face
Abstract
The 3D shape of human faces deform with time and contain rich aging information. However, in the literature, no work has been done with the 3D shape of face for age estimation. Thus, we propose in this paper to explore the 3D facial surface in age estimation. Based on Riemannian shape analysis of facial curves, we extract four types of Dense Scalar Field (DSF) descriptions from the 3D facial surface, which reflect the face Averageness, face Symmetry, and the Spatial and Gradient deviations of the face. Experiments are carried out following the Leave-One-Person-Out (LOPO) cross-validation on the earliest 466 scans in FRGCv2 dataset, using the Random Forest Regressor. With the DSF features, the proposed approach achieves 3.29 years Mean Absolute Error (MAE) in the gender-general experiments, and 3.15 years MAE in the gender-specific experiments. Results confirm the idea that the face aging differs with gender. To address the high dimensionality of DSF features and the imbalance in training instances, we propose to use a weighted PCA method. In both the gender-general and gender-specific experiments, the age estimation performances using weighted PCA are comparable to the performances using the DSF descriptions. While, the size of feature is significantly smaller with the weighted PCA.
Keywords
Age estimation 3D face Dense scalar field Principal component analysis Random forest regressionReferences
- 1.Criminisi, A., Shotton, J.: Regression forests. In: Criminisi, A., Shotton, J. (eds.) Decision Forests for Computer Vision and Medical Image Analysis, pp. 49–58. Springer, Berlin (2013)CrossRefGoogle Scholar
- 2.Samal, A., Subramani, V., Marx, D.: Analysis of sexual dimorphism in the human face. J. Vis. Comp. Imag. Rep. 18, 453–463 (2007)CrossRefGoogle Scholar
- 3.Fu, Y., Guo, G., Huang, T.S.: Age synthesis and estimation via faces: a survey. J. Pattern Anal. Mach. Intell. 11, 1955–1976 (2010). IEEEGoogle Scholar
- 4.Rhodes, M.G.: Age estimation of faces: a review. J. Appl. Cogn. Psyc. 23, 1–12 (2009)CrossRefGoogle Scholar
- 5.Guo, G., Mu, G., Fu, Y., Huang, T.S.: Human age estimation using bio-inspired features. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 112–119. IEEE (2009)Google Scholar
- 6.Han, H., Otto, C., Jain, A.K.: Age estimation from face images: human vs. machine performance. In: 6th International Conference on Biometrics, pp. 1–8 (2013)Google Scholar
- 7.Montillo, A., Ling, H.: Age regression from faces using random forests. In: 16th IEEE International Conference on Image Processing, pp. 2465–2468. IEEE (2009)Google Scholar
- 8.Phillips, P.J., Flynn, P.J., Scruggs, T., Bowyer, K.W., Chang, J., Hoffman, K., Marques, J., Min, J., Worek, W.: Overview of the face recognition grand challenge. In: IEEE Conference on Computer Vision and Pattern Recognition, vol. 1, pp. 947–954. IEEE (2005)Google Scholar
- 9.Srivastava, A., Klassen, E., Joshi, S.H., Jermyn, I.H.: Shape analysis of elastic curves in euclidean spaces. J. Pattern Anal. Mach. Intell. 33, 1415–1428 (2011). IEEECrossRefGoogle Scholar
- 10.Lanitis, A., Draganova, C., Christodoulou, C.: Comparing different classifiers for automatic age estimation. J. Syst. Man Cybern. Part B: Cybern. 34, 621–628 (2004). IEEECrossRefGoogle Scholar
- 11.Ueki, K., Sugiyama, M., Ihara, Y.: Perceived age estimation under lighting condition change by covariate shift adaptation. In: 20th International Conference on Pattern Recognition, pp. 3400–3403. IEEE (2010)Google Scholar
- 12.Lanitis, A., Taylor, C.J., Cootes, T.F.: Toward automatic simulation of aging effects on face images. J. Pattern Anal. Mach. Intell. 24, 442–455 (2002). IEEECrossRefGoogle Scholar
- 13.Geng, X., Zhou, Z.H., Smith-Miles, K.: Automatic age estimation based on facial aging patterns. J. Pattern Anal. Mach. Intell. 29, 2234–2240 (2007). IEEECrossRefGoogle Scholar
- 14.Ramanathan, N., Chellappa, R., Biswas, S.: Computational methods for modeling facial aging: a survey. J. Vis. Lang. Comp. 20, 131–144 (2009). ElsevierCrossRefGoogle Scholar
- 15.Albert, A.M., Ricanek, K., Patterson, E.: A review of the literature on the aging adult skull and face: implications for forensic science research and applications. J. Forensic Sci Int. 172, 1–9 (2007). ElsevierCrossRefGoogle Scholar
- 16.Park, U., Tong, Y., Jain, A.K.: Age-invariant face recognition. J. Pattern Anal. Mach. Intell. 32, 947–954 (2010). IEEECrossRefGoogle Scholar
- 17.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. IEEE (2008)Google Scholar
- 18.Guo, G., Fu, Y., Dyer, C.R., Huang, T.S.: Image-based human age estimation by manifold learning and locally adjusted robust regression. J. Imag. Process. 17, 1178–1188 (2008). IEEEMathSciNetCrossRefGoogle Scholar
- 19.Geng, X., Zhou, Z.H., Zhang, Y., Li, G., Dai, H.H.: Learning from facial aging patterns for automatic age estimation. In: 14th Annual ACM International Conference on Multimedia, pp. 307–316. ACM (2006)Google Scholar
- 20.The Relationship Between Age and Facial Asymmetry. http://meeting.nesps.org/2011/80.cgi
- 21.Cootes, T.F., Edwards, G.J., Taylor, C.J.: Active appearance models. In: Burkhardt, H., Neumann, B. (eds.) ECCV’98. LNCS, vol. 1407, pp. 484–498. Springer, Heidelberg (1998) CrossRefGoogle Scholar
- 22.N.S., L., J., B., Majumder, S.: Age estimation using gender information. In: Venugopal, K.R., Patnaik, L.M. (eds.) ICIP 2011. CCIS, vol. 157, pp. 211–216. Springer, Heidelberg (2011) CrossRefGoogle Scholar
- 23.Chao, W.L. Liu, J.Z., Ding, J.J.: Facial age estimation based on label-sensitive learning and age-specific local regression. In: IEEE International Conference on Acoustics, Speech and Signal Processing, pp. 1941–1944. IEEE (2012)Google Scholar
- 24.Suo, J.L., Zhu, S.C., Shan, S.G., Chen, X.L.: A compositional and dynamic model for face aging. J. Pattern Anal. Mach. Intell. 32, 385–401 (2010). IEEECrossRefGoogle Scholar
- 25.Tao, W., Turaga, P., Chellappa, R.: Age estimation and face verification across aging using landmarks. J. Info. Foren. Sec. 7, 1780–1788 (2012)CrossRefGoogle Scholar
- 26.Li, C.S., Liu, Q.S., Liu, J., Lu, H.Q.: Learning ordinal discriminative features for age estimation. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 2570–2577. IEEE (2012)Google Scholar
- 27.Mark, L.S., Todd, J.T.: The perception of growth in three dimensions. J. Atten. Percep. Psycho. 33, 193–196 (1983). SpringerCrossRefGoogle Scholar
- 28.Bruce, V., Burton, M., Doyle, T., Dench, N.: Further experiments on the perception of growth in three dimensions. J. Percept. Psycho. 46, 528–536 (1989). SpringerCrossRefGoogle Scholar
Copyright information
Open Access This chapter is distributed under the terms of the Creative Commons Attribution Noncommercial License, which permits any noncommercial use, distribution, and reproduction in any medium, provided the original author(s) and source are credited.