Local invariants and local constraints for face recognition

We propose a multiscale face recognition algorithm, robust to the geometrical distorsions of the images and to the changes of fighting conditions. A face is represented by a balanced set of points and each point is attributed with a local feature vector, based on the or orthogonal zernike moments, extracted at several scales. The similarity measure between two faces is a measure of the bust multiscale matching between those feature points of the two faces, each matching being obtained by dynamic programming. Experimental results shows the robustness of the method, under changes of expressions, fighting conditions, and inaccurate geometrical normalization.