Abstract A new offline signature verification system based on fuzzy modeling of multiple rules is proposed. In this system, both static and pseudodynamic features are extracted to make up for the loss of dynamic information and their variation is described by fuzzy sets. Then the new weight coefficients by the membership functions are devised to reflect the contribution of different fuzzy rules to verification results. In addition, the optimal selection of multiple rules by the reliable estimate of Kfold crossvalidation is presented to reduce the computational complexity of the entire fuzzy system. Databases of Chinese and English signatures are applied to the experiments and the average error rates of 9.52% and 12.67% are obtained. Thus the effectiveness of the proposed system is validated.
[1] Mizukami Y, Yoshimura M, Miike H, et al. An Offline Signature Verification System Using an Extracted Displacement Function. Pattern Recognition Letters, 2002, 23(13): 15691577 [2] Sabourin R, Chariet M, Genjest G. An Extended ShadowCode Based Approach for Offline Signature Verification // Proc of the 2nd International Conference on Document Analysis and Recognition. Tsukuba, Japan, 1993: 15 [3] Fang B, Leung C H, Tang Y Y, et al. Offline Signature Verification by the Tracking of Feature and Stroke Positions. Pattern Recognition, 2003, 36(1): 91101 [4] Deng P S, Liao H Y M, Ho C W, et al. WaveletBased Offline Handwritten Signature Verification. Computer Vision and Image Understanding, 1999, 76(3): 173190 [5] Lü Hairong, Wang Wenyuan, Wang Chong, et al. OffLine Chinese Signature Verification Based on Support Vector Machines. Pattern Recognition Letters, 2005, 26(15): 23902399 [6] Ferrer M A, Alonso J B, Travieso C M. Offline Geometric Parameters for Automatic Signature Verification Using FixedPoint Arithmetic. IEEE Trans on Pattern Analysis and Machine Intelligence, 2005, 27(6): 993997 [7] Watanabe S, Furuhashi T, Obata K, et al. A Study on Feature Extraction Using a Fuzzy Net for Offline Signature Recognition // Proc of the International Joint Conference on Neural Networks. Nagoya, Japan, 1993: 28572860 [8]Hanmandlu M, Yusof M H M, Madasu V K. Offline Signature Verification and Forgery Detection Using Fuzzy Modeling. Pattern Recognition, 2005, 38(3): 341356 [9] Hanmandlu M, Murali Mohan K R, Chakraborty S, et al. Fuzzy Modeling Based Signature Verification System // Proc of the 6th International Conference on Document Analysis and Recognition. Seattle, USA, 2001: 110114 [10] Babuska R, Verbruggen H B. Fuzzy Set Methods for Local Modeling and Identification // MurraySmith R, Johansen T A, eds. Multiple Model Approaches to Nonlinear Modeling and Control. London, UK: Taylor & Francis, 1997: 657662
2008, Vol. 21 
