FINGERPRINT CLASSIFICATION USING FUZZY CEREBELLAR MODEL ARITHMETIC COMPUTER NEURAL NETWORKS

We present some preliminary study results of an automated fingerprint pattern classification approach based on a novel neural network struct ure called the fuzzy cerebellar model arithmetic computer (CMAC) neura l network. The fingerprint images are first preprocessed to generate r idge flow, then the Karhunen-Loever (K-L) transform is used to extract the features from the ridge-flow images. The feature vector is then s ent to a fuzzy CMAC neural network for classification. Excellent resul ts were obtained through our preliminary experiments on the ''two clas ses'' problem. (C) 1997 SPIE and IS&T.