This paper includes an overview and experimental results on RST, the hybrid patteru classification system. It can recognize patterns even when they are deformed by a transformation like rotation, scaling, and translation or a combination of these . The system is formed of a Karhunen-Loeve transform based pattern preprocessor, an artificial neural network classifier and an interpreter. After a description of the system architecture, experimental results are provided from three different classification domains: classiflcation of letters in the English alphabet, classification of the letters in the Japanese Katakana alphabet, and classification of five main geometric figures. The system is general purpose and has a reasonable noise tolerance.