A Novel Approach to Combining Client-Dependent and Confidence Information in Multimodal Biometrics. Poh, N. & Bengio, S. In Kanade, T., Jain, A., & Ratha, N. K., editors, 5th International Conference on Audio- and Video-Based Biometric Person Authentication, AVBPA, Lecture Notes in Computer Science, volume LNCS 3546, pages 1120–1129, 2005. Springer-Verlag.
A Novel Approach to Combining Client-Dependent and Confidence Information in Multimodal Biometrics [link]Paper  abstract   bibtex   
The issues of fusion with client-dependent and confidence information have been well studied separately in biometric authentication. In this study, we propose to take advantage of both sources of information in a discriminative framework. Initially, each source of information is processed on a per expert basis (plus on a per client basis for the first information and on a per example basis for the second information). Then, both sources of information are combined using a second-level classifier, across different experts. Although the formulation of such two-step solution is not new, the novelty lies in the way the sources of prior knowledge are incorporated prior to fusion using the second-level classifier. Because these two sources of information are of very different nature, one often needs to devise special algorithms to combine both information sources. Our framework that we call ``Prior Knowledge Incorporation'' has the advantage of using the standard machine learning algorithms. Based on 10 times 32=320 intramodal and multimodal fusion experiments carried out on the publicly available XM2VTS score-level fusion benchmark database, it is found that the generalisation performance of combining both information sources improves over using either or none of them, thus achieving a new state-of-the-art performance on this database.
@inproceedings{poh:2005:avbpa:combining,
  author = {N. Poh and S. Bengio},
  title = {A Novel Approach to Combining Client-Dependent and Confidence Information in Multimodal Biometrics},
  booktitle = {5th International Conference on Audio- and Video-Based Biometric Person Authentication, {AVBPA}, Lecture Notes in Computer Science},
  editor = {T. Kanade and A. Jain and N. K. Ratha},
  publisher  = {Springer-Verlag},
  volume = {LNCS 3546},
  pages = {1120--1129},
  year = 2005,
  url = {publications/ps/poh_2005_avbpa_combining.ps.gz},
  pdf = {publications/pdf/poh_2005_avbpa_combining.pdf},
  djvu = {publications/djvu/poh_2005_avbpa_combining.djvu},
  idiap = {publications/pdf/rr04-68.pdf},
  original = {2005/fusion_combining_avbpa},
  topics = {biometric_authentication},
  web = {http://dx.doi.org/10.1007/11527923_116},
  abstract = {The issues of fusion with client-dependent and confidence information have been well studied separately in biometric authentication. In this study, we propose to take advantage of both sources of information in a discriminative framework. Initially, each source of information is processed on a per expert basis (plus on a per client basis for the first information and on a per example basis for the second information).  Then, both sources of information are combined using a second-level classifier, across different experts.  Although the formulation of such two-step solution is not new, the novelty lies in the way the sources of prior knowledge are incorporated prior to fusion using the second-level classifier.  Because these two sources of information are of very different nature, one often needs to devise special algorithms to combine both information sources.  Our framework that we call ``Prior Knowledge Incorporation'' has the advantage of using the standard machine learning algorithms.  Based on 10 times 32=320 intramodal and multimodal fusion experiments carried out on the publicly available XM2VTS score-level fusion benchmark database, it is found that the generalisation performance of combining both information sources improves over using either or none of them, thus achieving a new state-of-the-art performance on this database.},
  categorie = {C},
}

Downloads: 0