An efficient face identification method in a transformed domain

In this paper we propose a low-complexity face recognition system based on the Walsh-Hadamard transform. This system can be easily implemented on a fixed point processor and offers a good compromise between computational burden and identification rates. We have evaluated that with 169 integer coefficients per face we achieve better results (92%) than the classical eigenfaces approach (86.5%), and close to the DCT (92.5%) with a reduced computational cost. computational burden and memory requirements are still important. In order to alleviate this problem we have resized the original images from 112*92 to 56*46 for the KLT results. Geometry-feature-based methods try to identify the position and relationship between face parts, such as eyes, nose, mouth, etc., and the extracted parameters are measures of textures, shapes, sizes, etc. of these regions.