Elham Tabassi

Biometric Quality: the Last 1%: Biometric Quality Assessment for Error Suppression Elham Tabassi

Publisher Marketing: Performance of biometric recognition systems degrades substantially as quality of the input samples drops. Although only a small fraction of input data are of poor-quality, the bulk of recognition errors can be attributed to poor-quality samples. If quality can be improved, either by sensor design, by user interface design, or by standards compliance, better performance can be realized. For those aspects of quality that cannot be designed-in, an ability to analyze the quality of a live sample is needed. This is useful primarily in initiating the reacquisition from a user, but also for the real-time selection of the best sample, the selective invocation of different processing methods, or fusion. Accordingly, biometric quality measurement algorithms are increasingly deployed in operational systems, US-VISIT, PIV, and EU VIS each mandate the measurement and reporting of quality scores of captured images. With the increase in deployment of quality algorithms, the need to standardize an interoperable way to store and exchange biometric quality scores, and methods for evaluation the effectiveness of quality algorithms increases. This document describes NIST's activities on biometric sample quality research and standardization.