Online AUC learning for biometric scores fusion

Youngsung Kim, Kar Ann Toh

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Citation (Scopus)

Abstract

In biometric fusion systems, it is common to find the number of available imposter scores being much larger than the number of genuine-user scores. In terms of training a stable fusion classifier, the area under the receiver operating characteristic curve (AUC) could be useful since it is less sensitive to class distributions [1], [2], [3]. A direct optimization of this AUC criterion thus becomes a natural choice for fusion classifier design. However, a direct formulation of search based on the AUC criterion would have the incoming data size growing almost exponentially. In this paper, we propose an online learning algorithm to circumvent this computational problem in multi-biometric scores fusion. Since the proposed method involves pairing of data points of opposite classes, an online learning formulation becomes non-trivial. Our empirical results on two publicly available score-level fusion databases show promising potential in terms of verification AUC, Half Total Error Rate, Accuracy, and computational efficiency.

Original languageEnglish
Title of host publicationProceedings of the 2011 6th IEEE Conference on Industrial Electronics and Applications, ICIEA 2011
Pages275-280
Number of pages6
DOIs
Publication statusPublished - 2011 Sep 5
Event2011 6th IEEE Conference on Industrial Electronics and Applications, ICIEA 2011 - Beijing, China
Duration: 2011 Jun 212011 Jun 23

Publication series

NameProceedings of the 2011 6th IEEE Conference on Industrial Electronics and Applications, ICIEA 2011

Other

Other2011 6th IEEE Conference on Industrial Electronics and Applications, ICIEA 2011
CountryChina
CityBeijing
Period11/6/2111/6/23

All Science Journal Classification (ASJC) codes

  • Electrical and Electronic Engineering
  • Industrial and Manufacturing Engineering

Fingerprint Dive into the research topics of 'Online AUC learning for biometric scores fusion'. Together they form a unique fingerprint.

  • Cite this

    Kim, Y., & Toh, K. A. (2011). Online AUC learning for biometric scores fusion. In Proceedings of the 2011 6th IEEE Conference on Industrial Electronics and Applications, ICIEA 2011 (pp. 275-280). [5975594] (Proceedings of the 2011 6th IEEE Conference on Industrial Electronics and Applications, ICIEA 2011). https://doi.org/10.1109/ICIEA.2011.5975594