Artificial Aging of Faces by Support Vector Machines

In this research, we use Support Vector Machines (SVMs) in our system to automatically synthesize the aging effect on human facial images. The coordinates of the facial feature points are used to train the SVMs. Given a new picture, the displacement of the feature points is predicted according to different target ages in the future. The predictions are fed into a warping system to produce the synthesized aged facial images. The results of the prediction using SVMs are analyzed.

[1]  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.

[2]  Rama Chellappa,et al.  Human and machine recognition of faces: a survey , 1995, Proc. IEEE.

[3]  Timothy F. Cootes,et al.  Active Appearance Models , 2001, IEEE Trans. Pattern Anal. Mach. Intell..

[4]  Mikkel B. Stegmann,et al.  Analysis and segmentation of face images using point annotations and linear subspace techniques, in , 2002 .

[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]  Timothy F. Cootes,et al.  Toward Automatic Simulation of Aging Effects on Face Images , 2002, IEEE Trans. Pattern Anal. Mach. Intell..

[7]  J. B. Pittenger,et al.  Perceptual information for the age level of faces as a higher order invariant of growth. , 1979, Journal of experimental psychology. Human perception and performance.