DOI QR코드

DOI QR Code

On-line Signature Verification Using Fusion Model Based on Segment Matching and HMM

구간 분할 및 HMM 기반 융합 모델에 의한 온라인 서명 검증

  • 양동화 (충북대학교 전기전자컴퓨터공학부 컴퓨터정보통신연구소) ;
  • 이대종 (알바타대학교 전기컴퓨터공학과) ;
  • 전명근 (충북대학교 전기전자컴퓨터공학부 컴퓨터정보통신연구소)
  • Published : 2005.02.01

Abstract

The segment matching method shows better performance than the global and points-based methods to compare reference signature with an input signature. However, the segment-to-segment matching method has the problem of decreasing recognition rate according to the variation of partitioning points. This paper proposes a fusion model based on the segment matching and HMM to construct a more reliable authentic system. First, a segment matching classifier is designed by conventional technique to calculate matching values lot dynamic information of signatures. And also, a novel HMM classifier is constructed by using the principal component analysis to calculate matching values for static information of signatures. Finally, SVM classifier is adopted to effectively combine two independent classifiers. From the various experiments, we find that the proposed method shows better performance than the conventional segment matching method.

기존의 참조서명과 입력서명을 비교하는 방법 쿵 분절 단위 비교 방법은 전역적 방법과 점 단위 방법에 비하여 우수한 장점을 가지고 있다. 그러나 분절 단위 비교 방법은 인식률과 직접적인 관계가 있는 분절의 불안정 문제점이 있다. 본 연구에서는 분절 단위 비교 방법을 이용한 서명검증의 신뢰도를 향상시키기 위해 두 가지 형태의 모델을 구축하였다. 우선 기존에 사용된 구간 분할 매칭 방법을 사용하여 서명의 동적정보에 대한 매칭도를 산출하였다. 다음으로 서명의 정적정보를 균일하게 분할한 후 분할된 영역을 주성분 분석 기법에 의해 특징 벡터를 산출하고 HMM에 의해 서명간의 매칭도를 산출하였다. 최종 융합단계에서는 SVM 분류기에 의해 서명의 진위여부를 결정하도록 구축하였다. 실험 결과 제안된 기법은 분절단위 기반의 구간 분할 매칭 기법에 비해 우수한 성능을 나타냈다.

Keywords

References

  1. 전명근, 생체인식(Biometric) 총론, 한국정보통신교육원, pp. 7-1-7-29, 2004
  2. Chin-Chuan Han, 'An on-line signature verification system using multi-template matching approaches', Security Technology, Proceedings. IEEE 33rd Annual International Carnahan Conference on , pp. 477-480, 1999
  3. Ma Mingming, 'Automatic on-line signature verification based on multiple models', Computational Intelligence for Financial Engineering, (CIFEr) Proceedings of the IEEE/IAFE/INFORMS Conference on , pp. 30-33, 2000
  4. Rhee T.H., 'On-line signature verification using model-guided segmentation and discriminative feature selection for skilled forgeries', Proceedings. Sixth International Conference on , Document Analysis and Recognition, pp. 645-649, 2001
  5. Yue K. W. and Wijesoma W.S., 'Improved segmentation and segment association for on-line signature verification,' IEEE International Conference on, Systems, Man, and Cybernetics, Vol. 4, 2000
  6. Brault, J.-J. and Plamondon R., 'Segmenting handwritten signatures at their perceptually important points,' IEEE Transactions on , Pattern Analysis and Machine Intelligence, Vol. 15, No.9, 1993
  7. Schmidt C. and Kraiss K.-F., 'Establishment of personalized templates for automatic signature verification,' Proceedings of the Fourth International Conference on, Document Analysis and Recognition, Vol. 1, pp. 263-267, 1997
  8. Kiran G.V., Kunte R.S.R. and Samuel S., 'On-line signature verification system using probabilistic feature modelling,' , Sixth International, Symposium on, Signal Processing and its Applications, Vol. 1, pp. 355-358, 2001
  9. Sang-Yeun Ryu, Dae-Jong Lee, Myung-Geun Chun, 'A Robust On-line Signature Verification System', International Journal of Fuzzy Logic and Intelligent Systems, vol. 3, no. 1, pp.27-31, 2003 https://doi.org/10.5391/IJFIS.2003.3.1.027
  10. P. K. Belhumeur, J. P. Hespanha, D. J. Kriegmaqn, 'Eigenfaces vs. Fisherfaces : recognition using class specific Linear Projection', IEEE Trans. on Pattern Analysis and Machine Intell., 19(7), pp. 711-720, 1997 https://doi.org/10.1109/34.598228
  11. Richard O. Duda, Peter E. Hart, David G. Stork, Pattern Classification, JOHN WILEY &SONS, INC. Second Edition, 2002
  12. 민준오, 류상연, 곽근창, 전명근, '얼굴과 서명을 이용한 다중생체인식 시스템', BERC Biometircs Workshop, Vol. 1, pp. 141-145, 2004
  13. Viswanathan, R., Varshney, P.K., 'Distributed detection with multiple sensors I. Fundamentals', Proceedings of the IEEE, Vol. 85, pp. 54-63, 1997
  14. Krzysztofowicz, R., Long, D., 'Fusion of detection probabilities and comparison of multi sensor systerns', IEEE Transactions on, Systems, Man and Cybernetics, Vol. 20, pp. 665-677, 1990 https://doi.org/10.1109/21.57281
  15. Ben Yacoub, S., Abdeljaoued, Y., Mayoraz, E., 'Fusion of face and speech data for person identity verification', IEEE Transactions on Neural Networks, Vol. 10, pp. 1065-1074, 1999 https://doi.org/10.1109/72.788647