Image recognition using Simplified Fuzzy ARTMAP augmented with a moment based feature extractor

The capability of Kasuba's Simplified Fuzzy ARTMAP (SFAM) to behave as a Pa ttern Recognizer/Classifier of images both noisy and noise free has been in vestigated in this paper. This calls for augmenting the original Neuro-Fuzz y model with a modified moment-based RST invariant feature extractor. The potential of the SFAM based Pattern Recognizer to recognize patterns - monochrome and color, noisy and noise free - has been studied on two experi mental problems. The first experiment which concerns monochrome images, per tains to recognition of satellite images, a problem discussed by Wang et at . The second experiment, which concerns color images, deals with the recogn ition of some sample test colored patterns. The results of the computer sim ulation have also been presented.