Presents a feature recognition network for pattern recognition that learns the patterns by remembering their different segments. The base algorithm for this network is a Boolean net algorithm that the authors developed during past research. Simulation results show that the network can recognize patterns after significant noise, deformation, translation and even scaling. The network is compared to existing popular networks used for the same purpose, especially the Neocognitron. The network is also analyzed as regards to interconnection complexity and information storage/retrieval.>

A real-time system for position determination of a mobile robot in an industrial environment is presented. A complete error analysis of the system is conducted, and the necessary conditions required for achieving accuracy are evaluated mathematically. A method for segmentation using chromatic information has been developed. It makes extensive use of image moments to calculate geometric parameters and correct errors due to perspective distortion. Architectures for calculation of higher-order moments of up to seventh order in real time are discussed. Methods for performing these complex calculations in real time by using only simple circuit elements such as adders and accumulators are given.>