Online Signature Verification by Visualization of Dynamic Characteristics using New Pattern Transform Technique

동적 특성의 시각화를 수행하는 새로운 패턴변환 기법에 의한 온라인 서명인식 기술

  • 지수영 (한국전자통신연구원 지능형로봇연구단) ;
  • 이재연 (한국전자통신연구원 지능형로봇연구단) ;
  • 오원근 (한국전자통신연구원 콘텐츠보호연구팀) ;
  • 김창헌 (고려대학교 컴퓨터학과)
  • Published : 2005.07.01

Abstract

An analysis model for the dynamics information of two-dimensional time-series patterns is described. In the proposed model, two novel transforms that visualize the dynamic characteristics are proposed. The first transform, referred to as speed equalization, reproduces a time-series pattern assuming a constant linear velocity to effectively model the temporal characteristics of the signing process. The second transform, referred to as velocity transform, maps the signal onto a horizontal vs. vertical velocity plane where the variation oi the velocities over time is represented as a visible shape. With the transforms, the dynamic characteristics in the original signing process are reflected in the shape of the transformed patterns. An analysis in the context of these shapes then naturally results in an effective analysis of the dynamic characteristics. The proposed transform technique is applied to an online signature verification problem for evaluation. Experimenting on a large signature database, the performance evaluated in EER(Equal Error Rate) was improved to 1.17$\%$ compared to 1.93$\%$ of the traditional signature verification algorithm in which no transformed patterns are utilized. In the case of skilled forgery experiments, the improvement was more outstanding; it was demonstrated that the parameter set extracted from the transformed patterns was more discriminative in rejecting forgeries

본 논문에서는 서명패턴에 내재되어 있는 동적인 특성을 패턴변환을 이용하여 시각화 함으로써 위조서명에 대한 안정성을 향상시킨 새로운 온라인 서명인증 알고리즘을 제안한다. 제안하는 첫 번째 패턴변환방식인 속도 평활화(Speed Equalization)는 서명과정의 시간적인 특성을 효율적으로 모델링하기 위하여, 주어진 서명의 시계열 패턴을 선 속도가 일정하도록 재구성함으로써 변환된 패턴을 생성한다 한편 두 번째 패턴변환방식인 속도변환(Velocity Transform)은 주어진 서명패턴을 수평/수직 속도 평면으로 매핑 함으로써 변환된 패턴을 생성한다. 이러한 변환을 통하여 원래의 서명과정에서의 동적인 특성이 변환된 도메인에서는 변환된 패턴의 모양에 반영되게 되므로, 변환된 패턴에 대한 형체분석(Shape Analysis) 을 통하여 효율적으로 동적인 특성에 대한 분석이 이루어진다. 본 논문에서 제안하는 모델의 장점은 변환된 패턴들이 본래의 서명패턴과 동일한 형태로 표현된다는 점이다. 따라서 기존의 많은 연구를 통하여 제안되어 은 대부분의 서명인식 알고리즘을 변환된 패턴에도 그대로 적용할 수 있다는 장점을 가진다. 271명의 6770개의 서명패턴으로 이루어 진 데이타베이스를 대상으로 한 실험을 통하여 본 논문에서 제안된 방식을 사용한 경우, 1.17$\%$의 EER(Equal Error Rate)를 보여 제안된 변환을 사용하지 않은 경우의 1.93$\%$와 비교하여 성능이 현격하게 향상되었음을 보였다. 특히 위조서명에 대한 실험에서는 이 차이가 더욱 현저하여 본 논문에서 제안된 방식이 위조서명을 거부하는데 유용함을 보였다.

Keywords

References

  1. R. Kashi, J. Hu, W.L. Nelson, W. Turin.: A Hidden Markov Model Approach to online handwritten signature verification. International Journal on Document Analysis & Recognition, vol. 1, no. 2, (998) 102-109 https://doi.org/10.1007/s100320050010
  2. W. S. Wijesoma, M. Mingming, E. Sung.:Selecting Optimal Personalized Features for On-line Signature Verification Using GA. in Proc. SMC 2000, vol: 4, (2000) 2740-2745 https://doi.org/10.1109/ICSMC.2000.884411
  3. M.C. Fairhust, S. Ng,.: Management of access through biometric control: A case study based on automatic signature verification. Universal Access in the Information Society, vol. 1, no. 1, 2001 (31-39) https://doi.org/10.1007/s102090100009
  4. R. C. Gonzalez, P. Wintz. :Digital Image Processing. Addison-Wesley Publishing Company, Inc., (1977) 78-87
  5. T. Wessels and C.W.Omlin,.: A Hybrid System for Signature Verification. in Proc. IJCNN 2000, vol. 5, (2000) 509-514 https://doi.org/10.1109/IJCNN.2000.861520
  6. R.L. Burden, J. D. Faires. :Numerical Analysis. 5th ed., International Thomson Publishing, (1993) 57-168
  7. M.C.Fairhust.: Signature Verification Revisited: promoting practical exploitation of biometric technology. Electronics & Communication Engineering Journal, vol. 9, no. 6, (1997) 273-280 https://doi.org/10.1049/ecej:19970606
  8. R. Plamondon and G. Lorette. :Automatic Signature Verification and Writer Identification The State of the Art. Pattern Recognition, Vol. 22, No. 2, (1989) 107-131 https://doi.org/10.1016/0031-3203(89)90059-9
  9. F. Leclerc, R. Plamondon.: Automatic Signature Verification: The State of the Art 1989-1993. International Journal of Pattern Recognition & Artificial Intelligence, vol. 8, no. 3, (1994) 634-660
  10. R. Plamondon, S. Srihari. :On-Line and Off-Line Handwriting Recognition: A Comprehensive Survey. IEEE Trans. Pattern Analysis & Matchine Intelligence, vol. 22, no. 1, (2000) 63-84 https://doi.org/10.1109/34.824821
  11. K. Huang and H. Yan. :Off-Line Signature Verification based on Geometric Feature Extraction and Neural Network Classification. Pattern Recognition, vol. 30, no. 1, (1997) 9-17 https://doi.org/10.1016/S0031-3203(96)00063-5
  12. R. Martens, L. Classen.: Incorporating local consistency information into the online signature verification process. International Journal on Document Analysis & Recognition, vol. 1, no. 2, (1998) 110-115 https://doi.org/10.1007/s100320050011
  13. J. Ribeiro and G. Vasconcelos.: Off-Line Signature Verification Using an Auto-associator CascadeCorrelation Architecture. in Proc. International Joint Conference on Neural Networks, vol. 4, (1999) 2882-2886
  14. A. El-Yacoubi, E. J R. Justina, R. Sabourin, F. Bortolizzi.: Off-Line Signature Verification Using HMMs and Cross-Validation. Proc. Signal Processing Society Workshop 2000, vol. 2. (2000) 859-868 https://doi.org/10.1109/NNSP.2000.890166
  15. E. J. R. Justina, F. Bortolozzi, R. Babourin.: Off-line Signature Verification Using HMM for Random, Simple and Skilled Forgeries. Proc. 6th International Conf. on Document Analysis and Recognition, (2001) 1031-1034 https://doi.org/10.1109/ICDAR.2001.953942
  16. R. Sabourin, G. Genest and F. J Preteux.: OffLine Signature Verification by Local Granulometric Size Distributions. IEEE Trans. Pattern Analysis & Machine Intelligence, vol. 19, No.9. (1997) 976-988 https://doi.org/10.1109/34.615447
  17. V. Kecman.: Learning and Soft Computing. The MIT Press. (2001) 255-312
  18. K. Zhang, I. Pratikakis, J. Cornelis and E. Nyssen.: Using Landmarks to Establish a Point-to-Point Correspondence between Signatures. Pattern Analysis & Applications, vol. 3, no. 1, (2000) 69-74 https://doi.org/10.1007/s100440050007
  19. G. V. Kiran, R. S. Kunte, S. Samuel.: On-Line Signature Verification System Using Probablistic Feature Modeling. Proc. 6th International Symposium on Signal Processing and its Applications, vol. 1. (2001) 355-358 https://doi.org/10.1109/ISSPA.2001.949851