en Research Paper Research Paper <font face="TTE1DF74D0t00" size="2"><p align="left">Dealing with uncertainty is one of the most critical problems in complicated</p><p align="left">pattern recognition subjects. In this paper, we modify the structure of a useful Unsupervised</p><p align="left">Fuzzy Neural Network (UFNN) of Kwan and Cai, and compose a new FNN with 6 types of</p><p align="left">fuzzy neurons and its associated self organizing supervised learning algorithm. This</p><p align="left">improved five-layer feed forward Supervised Fuzzy Neural Network (SFNN) is used for</p><p align="left">classification and identification of shifted and distorted training patterns. It is generally</p><p align="left">useful for those flexible patterns which are not certainly identifiable upon their features. To</p><p align="left">show the identification capability of our proposed network, we used fingerprint, as the most</p><p align="left">flexible and varied pattern. After feature extraction of different shapes of fingerprints, the</p><p align="left">pattern of these features, “feature-map”, is applied to the network. The network first</p><p align="left">fuzzifies the pattern and then computes its similarities to all of the learned pattern classes.</p><p align="left">The network eventually selects the learned pattern of highest similarity and returns its</p><p align="left">specific class as a non fuzzy output. To test our FNN, we applied the standard (NIST</p><p align="left">database) and our databases (with 176×224 dimensions). The feature-maps of these</p><p align="left">fingerprints contain two types of minutiae and three types of singular points, each of them</p><p align="left">is represented by 22×28 pixels, which is less than real size and suitable for real time</p><p align="left">applications. The feature maps are applied to the FNN as training patterns. Upon its setting</p><p align="left">parameters, the network discriminates 3 to 7 subclasses for each main classes assigned to</p><p align="left">one of the subjects.</p></font> Classification,Fingerprint,Fuzzy Neural Network,Fuzzy Neurons,Identification,Supervised Learning Algorithm, 71 78 http://ijeee.iust.ac.ir/browse.php?a_code=A-10-3-62&slc_lang=en&sid=1 M. Hariri حریری 18003194753284600222 18003194753284600222 Yes S. B. Shokouhi شکوهی 18003194753284600223 18003194753284600223 No N. Mozayani مزینی 18003194753284600224 18003194753284600224 No