National Journal of System and Information Technology

Open Access Open Access  Restricted Access Subscription Access
Open Access Open Access Open Access  Restricted Access Restricted Access Subscription Access

Signature Recognitio N and Verification Using Artificial Neural Networks: a Comparative Study


     

   Subscribe/Renew Journal


The paper presents the comparative analysis of signature recognition and verification using Neural Networks. Three well-known and widely used Neural Networks viz. Support Vector Machines, Multilayer Perceptron and Radial Basis Function Network have been used. Each network differs from the other in the manner it approaches the signature given for recognition and verification. A signature database is collected using intrapersonal variations for evaluation. For every 6 training examples, 4 are used to test the signatures based on various features like false rejection rate, false acceptance rate, equal error rate, and average error rate. The merits and demerits of all the approaches are evaluated and hence the results of numerical experiments are given and analyzed in the paper. In this paper an off-line Recognition and Verification is done with the objective of performance comparison. The comparison of the three networks is done with respect to the complexity of the structure as well as the accuracy of expected results so that the forgeries can be minimized.

Keywords

Neural Networks, Offline Signature Verification, Multilayer Perception, Support Vector Machine, Radial Basis Function Network
Subscription Login to verify subscription
User
Notifications
Font Size


  • C.Cortes and V.Vapnik, “Support-vector networks. Machine Learning”, vol. 20, Nov. 1995.

  • E.J.R. Justino, F. Bortolozzi, and R. Sabourin. “A comparison of SVM and HMM classifiers in the off-line signature verification”, Pattern Recognition Letters 26, 2005.

  • G.K.Gupta, R.C.Joyce, “Using position extrema points to capture shape in on-line hand written signature verification”, Pattern Recognition, vol 40, pp. 2811 – 2817, 2007.

  • J. F. Vélez, Á. Sánchez , and A. B. Moreno, “Robust Off-Line Signature Verification Using Compression Networks And Positional Cuttings”, Proc. 2003 IEEE Workshop on Neural Networks for Signal Processing, vol. 1, pp. 627-636, 2003.

  • Joachims, T, “Text categorization with support vector machines: Learning with many relevant features”. Proceedings of the Tenth European Conference on Machine Learning.

  • K. Han, and I.K. Sethi, “Handwritten Signature Retrieval and Identification”, Pattern Recognition.

  • K. R Radhika, M K Venkatesha andG N Sekhar, “Pattern Recognition Techniques in Off-line hand written signature verification - A Survey”, proceedings of world academy of science, engineering and technology volume 36 December 2008.

  • L.E. Martinez, C.M. Travieso, J.B. Alonso, and M. Ferrer, “Parametrization of a forgery Handwritten Signature Verification using SVM”, IEEE 38th Annual 2004 International Carnahan Conference on Security Technology, 2004, pp. 193-196.

  • Stephane Armand, Michael Blumenstein and Vallipuram Muthukkumarasamy, “Offline Signature Verification based on the Modified Direction Feature”.


Abstract Views: 363

PDF Views: 2




  • Signature Recognitio N and Verification Using Artificial Neural Networks: a Comparative Study

Abstract Views: 363  |  PDF Views: 2

Authors

Abstract


The paper presents the comparative analysis of signature recognition and verification using Neural Networks. Three well-known and widely used Neural Networks viz. Support Vector Machines, Multilayer Perceptron and Radial Basis Function Network have been used. Each network differs from the other in the manner it approaches the signature given for recognition and verification. A signature database is collected using intrapersonal variations for evaluation. For every 6 training examples, 4 are used to test the signatures based on various features like false rejection rate, false acceptance rate, equal error rate, and average error rate. The merits and demerits of all the approaches are evaluated and hence the results of numerical experiments are given and analyzed in the paper. In this paper an off-line Recognition and Verification is done with the objective of performance comparison. The comparison of the three networks is done with respect to the complexity of the structure as well as the accuracy of expected results so that the forgeries can be minimized.

Keywords


Neural Networks, Offline Signature Verification, Multilayer Perception, Support Vector Machine, Radial Basis Function Network

References