Supervised fuzzy inference network for invariant pattern recognition

A supervised fuzzy inference network (FIN) model and its learning algorithm for invariant pattern recognition are presented in this paper. This fuzzy inference network is suitable for 2-D visual pattern recognition problems and has been tested with letter patterns of black and white pixel values. In contrast to most of the conventional pattern recognition systems, the proposed fuzzy inference network for pattern recognition does not require any pre-processing of feature extraction. Instead, the feature extraction step is incorporated in the structure of the network. The learning speed of the proposed fuzzy inference network is fast. The structure of the proposed fuzzy inference network is simple and it performs well when applied in invariant pattern recognition problems.