Abstract

Forgery detection has been a challenging area in the field of biometry, e. g. , handwritten signatures. Signature verification is a bi-objective optimization problem. The two crucial parameters are accuracy and time of computation. In this work, a comprehensive study on application of Adaptive Resonance Theory (ART) Nets (Type 1 and 2) and Associative Memory Net (AMN) has been conducted. To decrease the time complexity a corresponding parallel version using OpenMP is developed for each algorithm. The algorithms are trained with the original/genuine signature and tested with a sample of twelve very similar-looking forged signatures. The study concludes that ART-1 detects fake signatures with an accuracy of 99. 89%; whereas, ART-2 and AMN detect forgery with accuracies of 99. 99% and 75. 68% respectively which are comparable to other methods cited in this paper.

References

• T. Dash, T. Nayak, S. Chattopadhyay, Offline Verification of Hand Written Signature Using Adaptive Resonance Theory Net (Type-1), in Proc: IEEE Int. Conf. Electronics Computer Technology (ICECT) (2012), Vol-2, pp. 205-210.
• X. Xiao, G. Leedham, Signature verification using a modified Bayesian network, Pattern Recognition (2002) 35, 983-995.
• Y. Mizukami, M. Yoshimura, H. Miike, I. Yoshimura, An off-line signature verification system using an extracted displacement function, Pattern Recognition Letters (2002), 23, 1569-1577.
• A. Kholmatov, B. Yanikoglu, Identity authentication using improved online signature verification method, Pattern Recognition Letters (2005), 26, 1400-2408.
• J. C. M. Romo, R. A. Silva, Optimal Prototype functions of features for online signature verification, International Journal of Pattern Recognition and Artificial Intelligence, Volume: 18, Issue: 7(2004) pp. 1189-1206.
• M. Ammar, Progress in verification of skillfully simulated handwritten signatures, International Journal of Pattern Recognition and Artificial Intelligence, Volume: 5, Issues: 1-2(1991) pp. 337-351.
• H. Cardot, M. Revenu, B. Victorri, M. J. Revillet, A static signature verification system based on cooperating neural networks architecture, International Journal of Pattern Recognition and Artificial Intelligence, Volume: 8, Issue: 3(1994) pp. 679-692.
• B. Fang, X. You, W. S. Chen, Y. Y. Tang, Matching algorithm using wavelet thinning features for offline signature verification, International Journal of Pattern Recognition and Artificial Intelligence, Volume: 5, Issue: 1(2007) pp. 27-38.
• B. Fang, Y. Y. Wang, C. H. Leung, K. W. Tse, Y. Y. Tang, P. C. K. Kwok, Y. K. Wong, Offline signature verification by the analysis of cursive strokes, International Journal of Pattern Recognition and Artificial Intelligence, Volume: 15, Issue: 4(2001) pp. 659-673.
• S. Inglis, I. H. Witten, Compression-based Template Matching, in proc: IEEE Data Compression Conference (1994), pp. 106-115.
• M. K. Kalera, S. Srihari, A. Xu, Offline signature verification and identification using distance statistics, International Journal of Pattern Recognition and Artificial Intelligence, Volume: 18, 7(2004) pp. 1339-1360.
• N. S. Kamel, S. Sayeed, SVD-based signature verification technique using data glove, International Journal of Pattern Recognition and Artificial Intelligence, Volume: 22, 3(2008) pp. 431-443.
• J. Wen, B. Fang, Y. Y. Tang, P. S. P. Wang, M. Cheng, T. Zhang, Combining EODH and Directional Gradient Density for offline signature verification, International Journal of Pattern Recognition and Artificial Intelligence, Volume: 23, 6(2009) pp. 1161-1177.
• J. Bromley, J. W. Bentz, L. Bottou, I. Guyon, Y. Lecun, C. Moore, E. Sackinger, R. Shah, Signature Verificaiton using "SIAMESE" Time Delay neural network, International Journal of Pattern Recognition and Artificial Intelligence, Volume: 7, 4(1993) pp. 669-688.
• I. Yoshimura, M. Yoshimura, off-line signature of Japanese signatures after elimination of background patters, International Journal of Pattern Recognition and Artificial Intelligence, Volume: 8, 3(1994) pp. 693-708.
• W. Nelson, W. Turin, T. Hastie, Statistical method for on-line signature verification, International Journal of Pattern Recognition and Artificial Intelligence, Volume: 8, 3(1994) pp. 749-773.
• B. Li, D. Zhang, K. Wang, Online signature verification by combining shape contexts and local features, International Journal of Pattern Recognition and Artificial Intelligence, Volume: 6, 3(2006) pp. 407-420.
• M. S. Akshoy, H. Mathkour, Signature verification using rules 3-ext inductive learning system, International Journal of Physical Science, Vol. 6(18) (2011), pp. 4428-4434.
• S. Patil, S. Dewangan, Neural Network-based offline handwritten signature verification using Hu's moment invariant analysis, International Journal of Engineering and Advanced Technology, Vol. 1(1) (2011), pp. 73-79.
• L. Y. Tseng, T. H. Huang, An online Chinese signature verification scheme based on the ART1 neural network, in proc: Int. Conf. Neural Networks, vol. 3 (1992), pp. 624-630.
• P. Mautner, O. Rohlik, V. Matousek, J. Kempf, Signature verification using ART-2 neural network, in proc: 9th Int. Conf. Neural Information Processing, vol. 2 (2002), pp. 636- 639.
• T. Dash, S. Chattopadhyay, T. Nayak, "Handwritten Signature Verification using Adaptive Resonance Theory Type-2 (ART-2) Net". Journal of Global Research in Computer Science (2012) vol. 3 issue 8, pp. 21-25.
• T. Dash, T. Nayak, S. Chattopadhyay, "Offline Handwritten Signature Verification using Associative Memory Net". International Journal of Advanced Research in Computer Engineering & Technology (2012), vol. 1 issue 4, pp. 370-374.
• R. Chandra, L. Dagum, D. Kohr, D. Maydan, J. McDonald, R. Menon, Parallel programming in OpenMP, Morgan Kaufmann Publisher (2001). ISBN 1-55860-671-8.