Interval valued symbolic representation of writer dependent features for online signature verification |
| |
| Affiliation: | 1. Department of Studies in Computer Science, Manasagangothri, University of Mysore, Mysuru – 570 006, Karnataka, India;2. Department of Computer Science and Applications, Bangalore University, Bengaluru – 560 056, Karnataka, India;1. Imaging Media Research Center, Korea Institute of Science and Technology, Seoul 136-130, Republic of Korea;2. School of Electrical and Electronic Engineering, Yonsei University, Seoul 120-749, Republic of Korea;1. School of Electronics Engineering, Kyungpook National University, 1370 Sankyuk-Dong, Puk-Gu, Taegu 702-701, Republic of Korea;1. Laboratory of LESIA, University of Biskra, Algeria;2. University of the Basque Country, Spain;3. IKERBASQUE, Basque Foundation for Science, Spain;4. Laboratory of LAMIH, UMR CNRS 8201 UVHC, University of Valenciennes, France;5. Center for Machine Vision Research, University of Oulu, Finland;1. Department of Software Engineering and Information Technologies, École de Technologie Superieure, Montreal, Canada;2. Department of Computer Science and Mathematics, Lebanese American University, Beirut, Lebanon;1. Department of Computer Languages and System, University of Seville, Seville, Spain;2. Faculty of Maritme and Technology, Southampton Solent University, Southampton, United Kingdom;3. BCS Quality Specialist Group, United Kingdom |
| |
| Abstract: | This work focusses on exploitation of the notion of writer dependent parameters for online signature verification. Writer dependent parameters namely features, decision threshold and feature dimension have been well exploited for effective verification. For each writer, a subset of the original set of features are selected using different filter based feature selection criteria. This is in contrast to writer independent approaches which work on a common set of features for all writers. Once features for each writer are selected, they are represented in the form of an interval valued symbolic feature vector. Number of features and the decision threshold to be used for each writer during verification are decided based on the equal error rate (EER) estimated with only the signatures considered for training the system. To demonstrate the effectiveness of the proposed approach, extensive experiments are conducted on both MCYT (DB1) and MCYT (DB2) benchmarking online signature datasets consisting of signatures of 100 and 330 individuals respectively using the available 100 global parametric features. |
| |
| Keywords: | |
| 本文献已被 ScienceDirect 等数据库收录！ |
|
