The Community for Technology Leaders
Green Image
ABSTRACT
<p>An object recognition system based on the dynamic link architecture, an extension to classical artificial neural networks (ANNs), is presented. The dynamic link architecture exploits correlations in the fine-scale temporal structure of cellular signals to group neurons dynamically into higher-order entities. These entities represent a rich structure and can code for high-level objects. To demonstrate the capabilities of the dynamic link architecture, a program was implemented that can recognize human faces and other objects from video images. Memorized objects are represented by sparse graphs, whose vertices are labeled by a multiresolution 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. The implementation on a transputer network achieved recognition of human faces and office 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.</p>
INDEX TERMS
dynamic link architecture; object recognition system; artificial neural networks; fine-scale temporal structure; cellular signals; human faces; video images; sparse graphs; multiresolution description; local power spectrum; geometrical distance vectors; stochastic optimization; matching cost function; transputer network; gray-level camera images; face recognition; self-organising feature maps; transputer systems.
CITATION

R. Wurtz et al., "Distortion Invariant Object Recognition in the Dynamic Link Architecture," in IEEE Transactions on Computers, vol. 42, no. , pp. 300-311, 1993.
doi:10.1109/12.210173
85 ms
(Ver 3.3 (11022016))