Morphological shape decomposition is used to model a facial image region as a sum of components and to extract a feature vector at the nodes of a sparse grid overlaid over the facial area in dynamic link matching. The feature vector is comprised of the greylevel values at this node in the reconstructed images at several decomposition levels. This feature vector is subsequently employed in Dynamic Link Architecture to verify the identity of each person from a training set. The experimental results indicate that the proposed combination of morphological shape decomposition and dynamic link matching practically offers the same verification capability to the standard dynamic link matching with Gabor wavelets.
展开▼
