Performance Generalization in Biometric Authentication Using Joint User-Specific and Sample Bootstraps
Issue No. 03 - March (2007 vol. 29)
DOI Bookmark: http://doi.ieeecomputersociety.org/10.1109/TPAMI.2007.55
Samy Bengio , IEEE
Norman Poh , IEEE
Biometric authentication performance is often depicted by a detection error trade-off (DET) curve. We show that this curve is dependent on the choice of samples available, the demographic composition and the number of users specific to a database. We propose a two-step bootstrap procedure to take into account the three mentioned sources of variability. This is an extension to the Bolle et al.'s bootstrap subset technique. Preliminary experiments on the NIST2005 and XM2VTS benchmark databases are encouraging, e.g., the average result across all 24 systems evaluated on NIST2005 indicates that one can predict, with more than 75 percent of DET coverage, an unseen DET curve with eight times more users. Furthermore, our finding suggests that with more data available, the confidence intervals become smaller and, hence, more useful.
Biometric authentication assessment, DET, ROC, bootstrap subset.
Alvin Martin, Samy Bengio, Norman Poh, "Performance Generalization in Biometric Authentication Using Joint User-Specific and Sample Bootstraps", IEEE Transactions on Pattern Analysis & Machine Intelligence, vol. 29, no. , pp. 492-498, March 2007, doi:10.1109/TPAMI.2007.55