Illumination-invariant face recognition using composite filters synthesized by simulated annealing

The design of composite filters for illumination-invariant face recognition is discussed. As 3-D profiles have been extensively used as a way to ensur e this behavior, the two main constraints of 3-D analysis (i.e., 3-D profil e acquisition and the 3-D face-matching computational requirements) are con sidered. The first limitation is solved using a 3-D acquisition system base d on the projection of structured color light, which provides reliable 3-D data with a very simple setup. The second shortcoming is tackled by limitin g the recognition task to 2-D complexity, so the computational cost is redu ced. With the 3-D profile information available, 2-D training set images th at correspond to different illumination conditions are derived for the synt hesis of a 2-D composite filter using the simulated annealing algorithm. Th e experimental results confirm the potentiality of the proposed method. Add itionally, the concept of "average face" is presented and its feasibility a s an appropriate method for the recognition of a target from a set of objec ts is supported by experimental results. (C) 2000 Society of Photo-Optical Instrumentation Engineers. [S0091-3286(00)02005-5].