Journal of the Korea Society of Computer and Information (한국컴퓨터정보학회논문지)

Korean Society of Computer Information (한국컴퓨터정보학회)
권호 표지
DOI QR코드

DOI QR Code

An Automatic Signature Verification Algorithm for Smart Devices

  • Kim, Seong-Hoon (Dept. of Software, Kyungpook National University) ;
  • Fan, Yunhe (Dept. of Software, Kyungpook National University) ;
  • Heo, Gyeongyong (Dept. of Electronic Engineering, Dong-eui University)
  • Received : 2015.08.31
  • Accepted : 2015.09.30
  • Published : 2015.10.30
Download PDF
⟨ Previous Next ⟩

Abstract

In this paper, we propose a stable automatic signature verification algorithm applicable to various smart devices. The proposed algorithm uses real and forgery data all together, which can improve the verification rate dramatically. As a tool for signature acquisition in a smart device, two applications, one using touch with a finger and the other using a pressure-sensing-stylus pen, are developed. The verification core is based on SVM and some modifications are made to include the characteristics of signatures. As shown in experimental results, the minimum error rate was 1.84% in the SVM based method, which can easily defeat 4.38% error rate with the previous parametric approach. Even more, 2.43% error rate was achieved with the features excluding pressure-related features, better than the previous approach including pressure-related features and only about 0.6% more error than the best result, which means that the proposed algorithm can be applied to a smart device with or without pressure-sensing-stylus pens and used for security purposes.

Keywords

References

  1. R. Plamondon and G. Lorette, "Automatic Signature Verification and Writer Identification The State of The Art", Patten Recognition, vol. 22, no. 2, pp. 107-131, 1989. https://doi.org/10.1016/0031-3203(89)90059-9
  2. S. H. Kim, "A Technique of Calculating a Weighted Euclidean Distance with a Personalized Feature Set in Parametric Signature Verification", Journal of Korea Society for Simulation, vol. 14, no. 3, pp. 137-146, September 2005.
  3. D. H. Yang, D. J. Lee and M. G. Chun, "On-line Signature Verification Using Fusion Model Based on Segment Matching and HMM", Journal of Fuzzy Logic and Intelligent Systems, vol. 15, no. 1, pp.12-17, 2005. https://doi.org/10.5391/JKIIS.2005.15.1.012
  4. J. Kim, J. R. Yu and S. H. Kim, "Learning of Prototypes and Decision Boundaries for a Verification Problem have only Positive Samples,"Pattern Recognition Letters, Vol.17, pp.691-697, 1996. https://doi.org/10.1016/0167-8655(96)00016-5
  5. J. O. Min, D. J. Lee and M. G. Chun, "Multi-modal Biometrics System Based on Face and Signature by SVM Decision Rule", The KIPS transactions, vol. 11B, no. 7, pp. 885-892, Dec 2004. https://doi.org/10.3745/KIPSTB.2004.11B.7.885
  6. Vladimir Vapnik, Statistical Learning Theory, John Wiley & Sons, New York, 1998.
  7. Ashis Pradhan, "Support Vector Machine-A Survey," International Journal of Emerging Technology and Advanced Engineering, Vol. 2, No. 8, pp. 82-85, Aug. 2012.
  8. J. Park and T. Hong, "The Prediction of DEA based Efficiency Rating for Venture Business Using Multi-class SVM", Asia Pacific Journal lf Information System, vol. 19, no. 2, pp. 439-155, June 2009.
  9. M. K. Choi, H. G. Lee and S. C. Lee, "A new classification model of weighted SVM based on effectiveness", Korean Institute of Next Generation Computing, vol. 9, no. 1, pp. 63-73, February 2013.
  10. S. Y. Choi and H. C. Ahn, "Optimized Bankruptcy Prediction through Combing SVM with Fuzzy Theory", Journal of Digital Convergence, vol. 13, no. 3, pp. 155-165, Mar 2015. https://doi.org/10.14400/JDC.2015.13.3.155
  11. Z. G. Yan, Y. X. Yang and Y. J. Ding, "An Experimental Study of the Hyper-parameters Distribution Region and Its Optimization Method for Support Vector Machine with Gaussian Kernel", International Journal of Signal Processing, Image Processing and Pattern Recognition, vol. 6, no. 5, pp.437-446, 2013. https://doi.org/10.14257/ijsip.2013.6.5.38
  12. J. W. Lee D. H. Lee and I. S. Kim, "Method of Detecting Smishing using SVM", Journal of Security Engineering, vol. 10, no. 6, pp. 655-668, Dec 2013. https://doi.org/10.14257/jse.2013.12.01
  13. B. S. Kang, H. S. Jung, H. S. Lee, Y. H. Im, Y. W. Chung and D. H. Park, "Real Time Watch List Identification System using a Hybrid Hierarchical SVM", Journal of Security Engineering, vol. 7, no. 5, pp. 479-493, October 2010.
  14. Y. S. Hwang, J. C. Moon and S. J. Cho, "Classification of Malicious Web Pages by Using SVM", Journal of The Korean Society of Computer and Information, vol. 17, no. 3, pp. 77-83, March 2012.
  15. G. Y. Heo and S. H. Kim, "Context-Aware Fusion with Support Vector Machine", Journal of The Korean Society of Computer and Information, vol. 19, no. 6, pp. 19-26, June 2014.