Face Aging by Sparse Representation

Face aging aims at synthesizing one's face at different ages which interests many researchers in fields of cartoon animation, age estimation, face recognition, etc. However, modelling aging process is still challenging due to lack of robust features and a reasonable training set. In this paper we propose a novel automatic face aging approach through Maximum A Posteriori (MAP), a face is firstly warped by global geometric transformation, and then elder skin is locally synthesized by sparse coding. Our contribution includes an aging model both for children growth and adults aging, and high-level features by sparse representation aiming at a small training set while not downgrading the quality of synthesis. Moreover, the newly proposed features simplify the algorithm and lead to a fast implementation. Experiments show the proposed approach outperforms the existing methods.

[1]  Sung Yong Shin,et al.  On pixel-based texture synthesis by non-parametric sampling , 2006, Comput. Graph..

[2]  Bernard Tiddeman,et al.  Towards Realism in Facial Image Transformation: Results of a Wavelet MRF Method , 2005, Comput. Graph. Forum.

[3]  J T Todd,et al.  Perception of growth: a geometric analysis of how different styles of change are distinguished. , 1981, Journal of experimental psychology. Human perception and performance.

[4]  Daniel P. Huttenlocher,et al.  Comparing Images Using the Hausdorff Distance , 1993, IEEE Trans. Pattern Anal. Mach. Intell..

[5]  J. B. Pittenger,et al.  Aging faces as viscal-elastic events: implications for a theory of nonrigid shape perception. , 1975, Journal of experimental psychology. Human perception and performance.

[6]  Bernard Tiddeman,et al.  Prototyping and Transforming Facial Textures for Perception Research , 2001, IEEE Computer Graphics and Applications.

[7]  Jeremy S. De Bonet,et al.  Multiresolution sampling procedure for analysis and synthesis of texture images , 1997, SIGGRAPH.

[8]  Steven Fortune,et al.  Numerical stability of algorithms for 2-d Delaunay triangulations , 1995, Int. J. Comput. Geom. Appl..

[9]  Baining Guo,et al.  Real-time texture synthesis by patch-based sampling , 2001, TOGS.

[10]  Nadia Magnenat-Thalmann,et al.  Skin aging estimation by facial simulation , 1999, Proceedings Computer Animation 1999.

[11]  Christopher J. Solomon,et al.  Aging the human face - a statistically rigorous approach , 2005 .

[12]  Rama Chellappa,et al.  Modeling Age Progression in Young Faces , 2006, 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06).

[13]  Hans-Peter Seidel,et al.  A Generic Framework for Efficient 2-D and 3-D Facial Expression Analogy , 2007, IEEE Transactions on Multimedia.

[14]  Rajat Raina,et al.  Efficient sparse coding algorithms , 2006, NIPS.

[15]  D. Perrett,et al.  Perception of age in adult Caucasian male faces: computer graphic manipulation of shape and colour information , 1995, Proceedings of the Royal Society of London. Series B: Biological Sciences.

[16]  Zicheng Liu,et al.  Expressive expression mapping with ratio images , 2001, SIGGRAPH.

[17]  Patrick Pérez,et al.  Poisson image editing , 2003, ACM Trans. Graph..

[18]  Duncan Rowland,et al.  Manipulating facial appearance through shape and color , 1995, IEEE Computer Graphics and Applications.

[19]  Thomas S. Huang,et al.  Image super-resolution as sparse representation of raw image patches , 2008, 2008 IEEE Conference on Computer Vision and Pattern Recognition.

[20]  Daniel Thalmann,et al.  A dynamic wrinkle model in facial animation and skin ageing , 1995, Comput. Animat. Virtual Worlds.

[21]  Song-Chun Zhu,et al.  A Multi-Resolution Dynamic Model for Face Aging Simulation , 2007, 2007 IEEE Conference on Computer Vision and Pattern Recognition.

[22]  L. Farkas.  Anthropometry of the head and face , 1994 .