| Popis: |
The visual recognition system in animals is an inherently parallel system. Existing very large scale integrated circuit implementations have serious limitations on power consumption and computational speed. We propose a highly parallel optoelectronic system combining elements of the Grossberg and Dobbin vision models and Fukushima's Neocognitronmodel. This high performance machine vision hardware is capable of distortion invariant recognition. Modeling andimplementation of such systems provides insight into the visual recognition function, and also is useful for designing optoelectronic hardware that can be used for many applications. 1, INTRODUCTION In the field of neuroscience, many researchers study the structure of the human visual pathway and the visual cortexstructure However, it is not until recently, scientists have begun to provide comprehensive models of our visual system 4-6 Thus, a system based on the existing biological evidence to develop powerful recognition capability is now possible.Several efforts |
