UvA-DARE Expression-Invariant Age Estimation Expression-Invariant Age Estimation

In this paper, we investigate and exploit the influence of facial expressions on automatic age estimation. Different from existing approaches, our method jointly learns the age and the expression by introducing a new graphical model with a latent layer between the age/expression labels and the features. This layer aims to learn the relationship between the age and the expression and captures the face changes which induce the aging and the expression appearance, and thus obtaining expression-invariant age estimation. Conducted on two age-expression datasets (FACES [4] and Lifespan [10]), our experiments illustrate the improvement in performance when the age is jointly learnt with expression in comparison to expression-independent age estimation. The age estimation error is reduced by 14.43% and 37.75% for the FACES and Lifespan datasets respectively. Furthermore, the results obtained by our graphical model, without prior-knowledge of the expressions of the tested faces, are better that the best reported ones for both datasets.

[1]  Alan L. Yuille,et al.  The Concave-Convex Procedure (CCCP) , 2001, NIPS.

[2]  Yun Fu,et al.  Age Synthesis and Estimation via Faces: A Survey , 2010, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[3]  J. Daugman.  Uncertainty relation for resolution in space, spatial frequency, and orientation optimized by two-dimensional visual cortical filters. , 1985, Journal of the Optical Society of America. A, Optics and image science.

[4]  Xiaolong Wang,et al.  A study on human age estimation under facial expression changes , 2012, 2012 IEEE Conference on Computer Vision and Pattern Recognition.

[5]  Joris M. Mooij,et al.  libDAI: A Free and Open Source C++ Library for Discrete Approximate Inference in Graphical Models , 2010, J. Mach. Learn. Res..

[6]  Natalie C. Ebner,et al.  FACES—A database of facial expressions in young, middle-aged, and older women and men: Development and validation , 2010, Behavior research methods.

[7]  Chao Zhang,et al.  Age estimation with expression changes using multiple aging subspaces , 2013, 2013 IEEE Sixth International Conference on Biometrics: Theory, Applications and Systems (BTAS).

[8]  P. Ekman,et al.  Facial action coding system: a technique for the measurement of facial movement , 1978 .

[9]  Matti Pietikäinen,et al.  Multiresolution Gray-Scale and Rotation Invariant Texture Classification with Local Binary Patterns , 2002, IEEE Trans. Pattern Anal. Mach. Intell..

[10]  Thomas S. Huang,et al.  Human age estimation using bio-inspired features , 2009, CVPR.

[11]  Denise C. Park,et al.  A lifespan database of adult facial stimuli , 2004, Behavior research methods, instruments, & computers : a journal of the Psychonomic Society, Inc.

[12]  Xin Li,et al.  Facial Expression Recognition Influenced by Human Aging , 2013, IEEE Transactions on Affective Computing.

[13]  Kang Ryoung Park,et al.  Age estimation using a hierarchical classifier based on global and local facial features , 2011, Pattern Recognit..

[14]  Karl Ricanek,et al.  MORPH: a longitudinal image database of normal adult age-progression , 2006, 7th International Conference on Automatic Face and Gesture Recognition (FGR06).

[15]  Haizhou Ai,et al.  Demographic Classification with Local Binary Patterns , 2007, ICB.

[16]  Thorsten Joachims,et al.  Learning structural SVMs with latent variables , 2009, ICML '09.

[17]  Thomas S. Huang,et al.  Human age estimation using bio-inspired features , 2009, 2009 IEEE Conference on Computer Vision and Pattern Recognition.

[18]  Thomas Hofmann,et al.  Large Margin Methods for Structured and Interdependent Output Variables , 2005, J. Mach. Learn. Res..