Abstract
The estimation of human age from face images has many real-world applications. However, how to discover the intrinsic aging trend is still a challenging problem. We proposed a general distance metric learning scheme for regression problems, which utilizes not only data themselves, but also their corresponding labels to strengthen the credibility of distances. This metric could be learned by solving an optimization problem. Via the learned metric, it is easy to find the intrinsic variation trend of data by a relative small amount of samples without any prior knowledge of the structure or distribution of data. Furthermore, the test data could be projected to this metric by a simple linear transformation and it is easy to be combined with manifold learning algorithms to improve the performance. Experiments are conducted on the public FG-NET database by Gaussian process regression in the learned metric to validate our framework, which shows that its performance is improved over traditional regression methods.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
FG-NET Aging Database, http://www.fgnet.rsunit.com
Balasubramanian, V.N., Ye, J., Panchanathan, S.: Biased manifold embedding: A framework for person-independent head pose estimation. In: IEEE Conf. CVPR, pp. 1–7 (2007)
Bar-Hillel, A., Weinshall, D.: Learning distance function by coding similarity. In: Proc. ICML, pp. 65–72 (2007)
Belkin, M., Niyogi, P., Sindhwani, V.: Manifold regularization: a geometric framework for learing from labeled and unlabeled examples. Journal of Machine Learning Research 7, 2399–2434 (2006)
Cai, D., He, X., Han, J., Zhang, H.J.: Orthogonal laplacianfaces for face recognition. IEEE Trans. Image Processing 15, 3608–3614 (2006)
Cootes, T., Edwards, G., Taylar, C.: Active appearance models. IEEE Trans. Pattern Analysis & Machine Intelligence 23(6), 681–685 (2001)
Cox, T., Cox, M.: Multidimensional Scaling. Chapman & Hall, London (1994)
Deffenbacher, K.A., Vetter, T., Johanson, J., O’Toole, A.J.: Facial aging, attractiveness, and aistinctiveness. Perception 27 (1998)
Donoho, D.L., Grimes, C.E.: When does geodesic distance recover the true hidden parametrization of families of articulated images? In: Proc. European Symposium on Artificial Neural Networks (2002)
Draganova, A.L.C., Christodoulou, C.: Comparing different classifiers for automatic age estimation. IEEE Trans. Systems, Man, and Cybernetics 34(1), 621–628 (2004)
Duda, R.O., Hart, P.E., Stork, D.G.: Pattern Classification, 2nd edn. John Wiley & Sons, Inc., New York (2001)
Geng, X., Smith-Miles, K., Zhou, Z.-Z.: Facial age estimation by nonlinear aging pattern subspace. In: Proc. ACM Conf. Multimedia (2008)
Geng, X., Zhou, Z.H., Zhang, Y., Li, G., Dai, H.: Learning from facial aging patterns for automatic age estimation. In: Proc. ACM Conf. Multimedia, pp. 307–316 (2006)
Goldberger, J., Roweis, S., Hinton, G., Salakhutdinov, R.: Neighbourhood components analysis. In: NIPS (2005)
Golub, G.H., Loan, C.F.V.: Matrix Computations. Johns Hopkins Univ. Press (1996)
Guo, G., Fu, Y., Dyer, C., Huang, T.S.: Image-based human age estimation by manifold learning and locally adjusted robust regression. IEEE Trans. on Image Processing 17, 1178–1188 (2008)
Lanitis, A., Taylor, C.J., Cootes, T.: Toward automatic simulation of aging effects on face images. IEEE Trans. Pattern Analysis and Machine Intelligence 24(4), 442–455 (2002)
Neal, R.M.: Monte carlo implementation of gaussian process models for bayesian regression and classification. Technical Report CRG-TR-97-2
Nilsson, J., Sha, F., Jordan, M.I.: Regression on manifolds using kernel dimension reduction. In: IEEE Conf. ICML, pp. 265–272 (2007)
Raumussen, C.E., Williams, C.K.: Gaussian Processes for Machine Learning. MIT Press, Cambridge (2006)
Roweis, S.T., Saul, L.K.: Nonlinear dimensionality reduction by locally linear embedding. Science 290(5500), 2323–2326 (2000)
Scholkopf, B., Smola, A.J.: Learning with Kernels: Support Vector Machines, Regularization, Optimization, and Beyond. MIT Press, Cambridge (2002)
Sugiyama, M., Hachiya, H., Towell, C., Vijayakumar, S.: Geodesic gaussian kernels for value function approximation. Autonomous Robots 25, 287–304 (2008)
Tenebaum, J.B., de. Silva, V., Langford, J.C.: A global geometric framework for nonlinear dimensionally reduction. Science 290(5500), 2319–2323 (2000)
Weinberger, K., Blitzer, J., Saul, L.: Distance metric learning for large margin nearest neighbor classification. In: Proc. NIPS, pp. 1475–1482 (2006)
Xing, E., Ng, A., Jordan, M.I., Russell, S.: Distance metric learning with application to clustering with side-information. In: Proc. NIPS (2002)
Yan, S., ang, H.W., Huang, T.S., Tang, X.: Ranking with uncertain labels. In: IEEE Conf. Mulitimedia and Expo, pp. 96–99 (2007)
Yan, S., Wang, H., Tang, X., Huang, T.S.: Learning autostructured regressor from uncertain nonnegative labels. In: IEEE Conf. ICCV, pp. 1–8 (2007)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2009 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Pan, L. (2009). Human Age Estimation by Metric Learning for Regression Problems. In: Cremers, D., Boykov, Y., Blake, A., Schmidt, F.R. (eds) Energy Minimization Methods in Computer Vision and Pattern Recognition. EMMCVPR 2009. Lecture Notes in Computer Science, vol 5681. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-03641-5_34
Download citation
DOI: https://doi.org/10.1007/978-3-642-03641-5_34
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-03640-8
Online ISBN: 978-3-642-03641-5
eBook Packages: Computer ScienceComputer Science (R0)