ABSTRACT
In order to improve the accuracy of online signature verification, an online signature verification technology based on multi-mode matching is proposed. Combined with dynamic time warping (DTW) and string editing distance (SED), the average value, maximum value, minimum value and median value of the distance between the signatures to be tested and the signature of the template were calculated respectively. After normalization, it was combined into eight-dimensional feature vectors, and the experiment was carried out using SVM classifier. The experiment eventually achieved 1.25% FAR and FRR on SVC2004 Task2.
- Plamondon, R., A kinematic theory of rapid human movements. Biological cybernetics, 1995. 72(4): p. 295-307.Google Scholar
- Fang, Y., , A novel video-based system for in-air signature verification. Computers & Electrical Engineering, 2017. 57: p. 1-14.Google Scholar
- Fierrez-Aguilar, J., An Off-line Signature Verification System Based on Fusion of Local and Global Information. in International Workshop on Biometric Authentication. 2004.Google Scholar
- Richiardi, J., H. Ketabdar and A. Drygajlo. Local and global feature selection for on-line signature verification. 2005: IEEE.Google Scholar
- Tolosana, R., , Preprocessing and feature selection for improved sensor interoperability in online biometric signature verification. IEEE Access, 2015. 3: p. 478-489.Google Scholar
- Van, B.L., S. Garcia-Salicetti and B. Dorizzi, On using the Viterbi path along with HMM likelihood information for online signature verification. IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics), 2007. 37(5): p. 1237-1247.Google Scholar
- Kholmatov, A. and B. Yanikoglu, Identity authentication using improved online signature verification method. Pattern recognition letters, 2005. 26(15): p. 2400-2408.Google Scholar
- Fayyaz, M., Online signature verification based on feature representation. 2015: IEEE.Google Scholar
- Ahrabian, K. and B. BabaAli, Usage of autoencoders and Siamese networks for online handwritten signature verification. Neural Computing and Applications, 2019. 31(12): p. 9321-9334.Google Scholar
- Chevyrev, I. and A. Kormilitzin, A primer on the signature method in machine learning. arXiv preprint arXiv:1603.03788, 2016.Google Scholar
- Lai, S. and L. Jin, Recurrent adaptation networks for online signature verification. IEEE Transactions on Information Forensics and Security, 2018. 14(6): p. 1624-1637.Google Scholar
- Riesen, K. and R. Schmidt, Online signature verification based on string edit distance. International Journal on Document Analysis and Recognition (IJDAR), 2019. 22(1): p. 41-54.Google ScholarDigital Library
- Yeung, D., SVC2004: First international signature verification competition. 2004: Springer.Google Scholar
- Tan Hua, HE Lang.et al. On - line Signature Verification Based on Curvature [J]. Journal of Wuhan University of TechnologyInformation Management Engineering, 2017(1).Google Scholar
- Chenghua, L., , Feature Extraction Method for On-Line Handwriting Signature Based on EMD and SVD. Journal of South-Central University for Nationalities (Natural Science Edition), 2016(1): p. 20.Google Scholar
- Alpar, O., Online signature verification by continuous wavelet transformation of speed signals. Expert Systems with Applications. 104(aug.): p. 33-42.Google Scholar
Recommendations
An efficient online signature verification scheme using dynamic programming of string matching
ICHIT'11: Proceedings of the 5th international conference on Convergence and hybrid information technologyThe necessity to authenticate individuals is rapidly increasing day by day with the explosive growth of E-commerce, E-finance, PDA, etc. Handwritten signature is the most widely used and easiest way to verify a person. Online signature verification is a ...
Random forgery attacks against DTW-based online signature verification algorithm
SAC '11: Proceedings of the 2011 ACM Symposium on Applied ComputingSkilled forged signatures are one of the most difficult to distinguish from genuine signatures and randomly forged signatures are considered to be less difficult than skilled forged signatures. However, since the FARs are generally calculated by ...
A novel biometric system for signature verification based on score level fusion approach
AbstractThe active modality of handwriting is broadly related to signature verification in the context of biometric user authentication systems. Signature verification aims to verify a questioned signature as being genuine or forged compared to some ...
Comments