Probabilistic cellular automata in pattern recognition

The authors describe a new pattern recognition method that will allow for a synthesis of approaches based on prior analyses and contextual information with those based on artificial neural networks. They develop an iterative neural network framework based on a fully parallel probabilistic feedback dynamics. The method allows knowledge about the problem to be built into the network structure. Heuristic search techniques can be incorporated by modifying the probabilistics. The authors illustrate this method with a pattern recognition problem on an infrared image. The performance is better than that of competing methods.<>