A Study on the Consistency of Features for On-Line Signature Verification
A lot of different features have been proposed for on-line signature verification. By using these features, researchers implicitly believe they have high consistency as well as high discriminatory power. However, very little work has been done to measure the real consistency of these features. In this paper, we propose a model for consistency measure. Experiments were conducted to compare a comprehensive set of features commonly used for on-line signature verification.
KeywordsDecision Boundary Dynamic Time Warping Feature Distance Consistency Model Equal Error Rate
- 2.Munich, M., Perona, P.: Visual identification by signature tracking. IEEE Trans. on Pattern Analysis and Machine Intelligence (2003)Google Scholar
- 3.Martens, R., Claesen, L.: On-line signature verification by dynamic time-warping. In: Proc. 13th Int. Conf. Pattern Recognition, pp. 38–42 (1996)Google Scholar
- 4.Lee, L., Berger, T., Aviczer, E.: Reliable On-Line Human Signature Verification Systems. IEEE Trans. on Pattern Analysis and Machine Intelligence, pp. 643–647 (1996)Google Scholar
- 5.Rhee, T., Cho, S., Kim, J.: On-Line Signature Verification Using Model-Guided Segmentation and Discriminative Feature Selection for Skilled Forgeries. In: The 6th Int. Conf. on Document Analysis and Recognition, ICDAR (2001)Google Scholar
- 6.SVC. The First International Signature Verification Competition (2004), http://www.cs.ust.hk/svc2004/