Face recognition by elastic bunch graph matching

(http://www.neuroinformatik.ruhr-uni-bochum.de), when this research was performed. He is now at the Computational Neurobiology Laboratory, The Salk Institute for Biological Studies, San Diego, CA 92186-5800. E-mail: wiskott@cnl.salk.edu. • J.-M. Fellous was with the Computer Science Department, University of Southern California, Los Angeles, CA 90089 when this research was performed. He is now at the Volen Center for Complex Systems, Brandeis University, Waltham, MA 02254-9110. E-mail: fellous@cajal.ccs.brandeis.edu. • N. Krüger and C. von der Malsburg are with the Institute for Neural Computation, Bochum. Christoph von der Malsburg is also with the Computer Science Department, University of Southern California, Los Angeles. Email: {nkrueger, malsburgl@neuroinformatik.ruhr-uni-bochum.de. We present a system for recognizing human faces from single images out of a large database containing one image per person. Faces are represented by labeled graphs, based on a Gabor wavelet transform. Image graphs of new faces are extracted by an elastic graph matching process and can be compared by a simple similarity function. The system differs from the preceding one [1] in three respects. Phase information is used for accurate node positioning. Object-adapted graphs are used to handle large rotations in depth. Image graph extraction is based on a novel data structure, the bunch graph, which is constructed from a small set of sample image graphs.