FACE RECOGNITION BY ELASTIC BUNCH GRAPH MATCHING

We present a system for recognizing human faces from single images out of a large database containing one image per person. Faces are repres ented by labeled graphs, based on a Gabor wavelet transform. Image gra phs of new faces are extracted by an elastic graph matching process an d can be compared by a simple similarity function. The system differs from the preceding one [1] in three respects. Phase information is use d for accurate node positioning. Object-adapted graphs are used to han dle large rotations in depth. Image graph extraction is based on a nov el data structure, the bunch graph, which is constructed from a small set of sample image graphs.