We present a system for recognizing human faces from single images out of a large database containing one image per person. The task is difficult because of image variation in terms of position, size, expression, and pose. The system collapses most of this variance by extracting concise face descriptions in the form of image graphs. In these, fiducial points on the face (eyes, mouth, etc.) are described by sets of wavelet components (jets). Image graph extraction is based on a novel approach, the bunch graph, which is constructed from a small set of sample image graphs. Recognition is based on a straightforward comparison of image graphs. We report recognition experiments on the FERET database as well as the Bochum database, including recognition across pose.

|We present an object recognition system based on the Dynamic Link Architecture, which is an extension to classical Arti cial Neural Networks. The Dynamic Link Architecture exploits correlations in the ne-scale temporal structure of cellular signals in order to group neurons dynamically into higher-order entities. These entities represent a v ery rich structure and can code for high level objects. In order to demonstrate the capabilities of the Dynamic Link Architecture we implemented a program that can recognize human faces and other objects from video images. Memorized objects are represented by sparse graphs, whose vertices are labeled by a multi-resolution description in terms of a local power spectrum, and whose edges are labeled by geometrical distance vectors. Object recognition can be formulated as elastic graph matching, which is performed here by stochastic optimization of a matching cost function. Our implementation on a transputer network successfully achieves recognition of human faces and o ce objects from gray level camera images. The performance of the program is evaluated by a statistical analysis of recognition results from a portrait gallery comprising images of 87 persons. Index Terms|Computer vision, distortion invariance, dynamic link architecture, elastic graph matching, object recognition, neural network, wavelet.

A summary of brain theory is given so far as it is contained within the framework of Localization Theory. Di culties of this conventional theory" are traced back to a speci c de ciency: there is no way to express relations between active cells as for instance their representing parts of the same object. A new theory is proposed to cure this de ciency. It introduces a new kind of dynamical control, termed synaptic modulation, according to which synapses switch between a conducting and a nonconducting state. The dynamics of this variable is controlled on a fast time scale by correlations in the temporal ne structure of cellular signals. Furthermore, conventional synaptic plasticity is replaced by a re ned version. Synaptic modulation and plasticity form the basis for short-term and long-term memory, respectively. Signal correlations, shaped by the variable network, express structure and relationships within objects. In particular, the gure-ground problem may be solved in this way. Synaptic modulation introduces exibility i n to cerebral networks which is necessary to solve the invariance problem. Since momentarily useless connections are deactivated, interference between di erent memory traces can be reduced, and memory capacity increased, in comparison with conventional associative memory.

No abstract