A neuro-expert architecture for object recognition

Abstract

Summary form only given, as follows. A report is presented on results of experiments in object recognition with a combined neural network/expert system architecture (neuro-expert). The neuro-expert architecture is outlined with a description of the experimental object recognition system. Results are reported for the recognition of a 20-pattern prototype set of synthesized binary images placed at arbitrary rotations. A 100% recognition rate was obtained under noiseless conditions. Addition of 1% and 2% random pixel noise resulted in recognition rates of 95.2% and 89.5%, respectively.<>