A new signature verification technique based on a two-stage neural networkclassifier

This paper presents a new technique for off-line signature recognition and verification. The proposed system is based on global, grid and texture feat ures. For each one of these feature sets a special two stage Perception OCO N (one-class-one-network) classification structure has been implemented. In the first stage, the classifier combines the decision results of the neura l networks and the Euclidean distance obtained using the three feature sets . The results of the first-stage classifier feed a second-stage radial base function (RBF) neural network structure, which makes the final decision. T he entire system was extensively tested and yielded high recognition and ve rification rates. (C) 2001 Elsevier Science Ltd. All rights reserved.