Super-Resolution in Tensor Space and Active Appearance Model Based Simulation of Adult Aging Effects on Face Images

The applications of the simulation of adult aging effects are widespread nowadays whereas the difficulties in certain aspects restrict its development. In this paper, a method for simulating adult face aging effects is proposed. We adopt and extend an aging simulation method based on the super-resolution in tensor space. By means of the active appearance model, the differences among the locations and the shapes of the facial components are eliminated, with the background pixels wiped out before the aging simulation process. Texture variations and slight shape changes during aging process are added to the test image using super-resolution method while considerable shape changes are calculated separately based on AAM. The results of the simulation of aging effects in our method are evaluated by comparisons to the original images of the same individuals in the same age group and to the results obtained using the method we make improvements on.