Biometric User Authentication for IT Security: From Fundamentals to Handwriting (Advances in Information Security)
Handbook of Multibiometrics (International Series on Biometrics)
Handbook of Multibiometrics (International Series on Biometrics)
Handwriting verification - Comparison of a multi-algorithmic and a multi-semantic approach
Image and Vision Computing
CMS'10 Proceedings of the 11th IFIP TC 6/TC 11 international conference on Communications and Multimedia Security
CMS'12 Proceedings of the 13th IFIP TC 6/TC 11 international conference on Communications and Multimedia Security
| Hi-index | 0.00 |
Nowadays, multi-biometric fusion is a recent topic in biometric signal processing. The main goal is to optimize the authentication performance by combining different biometric components, e.g. modalities or algorithms. In this paper we only focus on fusion methods for online handwriting biometrics and compare three different fusion approaches. The methodologies are based on the combination of two dfferent handwriting verification algorithms, two different representations of the same semantic or two different semantics contents, whereby in context of biometric handwriting, semantics are alternative written contents. The evaluation of the three fusion approaches is carried out on a uniform test set based on dynamic handwriting data acquired from 84 users. The results show, that any of the three strategies leads to improvements with respect to the verification performance measure used (equal error rate, EER). In the best cases the relative improvement increases from 17% to 36% for single-semantic fusion and from 57% to 66% for multi-semantic fusion.