Performance of biometric systems is dependent on the quality of the acquired input 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, and the selective invocation of different processing methods. It is the key component in quality assurance management, and because quality algorithms often embed the same image (or signal) analyses needed to assess conformance to underlying data interchange standards, they can be used in automated image screening applications.
Quality analysis is a technical challenge because it is most helpful when the measures reflect the performance sensitivities of one or more target biometric matchers. NIST addressed this problem in August 2004 when it issued the NIST Fingerprint Image Quality algorithm, which was designed to be predictive of the performance of minutiae matchers. Since then NIST has been considering how quality measures should be evaluated, developing quality measures for other biometrics, and considering the wider use of such measures. In addition NIST is active in the ISO/IEC JTC1 SC37 standardization activities on biometric quality and sample conformance (ISO/IEC 29794).
Face recognition accuracy has improved markedly due to development of new recognition algorithms and approaches. Nevertheless, recognition error rates remain significantly above zero, particularly in applications where photography of faces is difficult or when stringent thresholds must be applied to recognition outcomes to reduce false positives. For those applications that retain an image as an authoritative reference sample against which future recognitions are done, it is critical to maintain database quality. While standards exist for interchange of face images, and those standards additionally regulate the capture of images, there are no standards for how face image quality must be assessed nor are there performance evaluations for automated quality assessment algorithms.
NFIQ was developed in 2004 to produce a quality value from a fingerprint image that is directly predictive of expected matching performance. With advances in fingerprint technology since 2004, an update to NFIQ is needed. A workshop was held in March 2010 at NIST to address the technical status of fingerprint quality assessment technology, and to engage industry to improve core finger image quality assessment technology based on lessons learned from recent deployments of quality assessment algorithms (including NFIQ) in large-scale identity management applications. Options for the future of NFIQ were discussed and the community overwhelmingly recommended a new (open source) version of NFIQ to be developed in consultation and collaboration with users and industry. To that end, National Institute of Standards and Technology (NIST) and Bundesamt für Sicherheit in der Informationstechnik (BSI) in Germany teamed up to develop the new and improved open source NIST Finger Image Quality (NFIQ 2).
The Iris Experts Group (IEG) is a forum for the discussion of technical questions of interest to USG agencies and their staff that are employing or may employ iris recognition to carry out their mission. Quality of iris capture is an important aspect discussed by the IEG.
27-29 October 2020: International Face Performance Conference (2020)
27-29 November 2020: International Face Performance Conference (2018)
03-05 May 2016: International Biometric Performance Testing Conference (2016)
01-03 April 2014: International Biometric Performance Testing Conference (2014)
05-09 May 2012: International Biometric Performance Testing Conference (2012)
02-04 March 2010: IBPC2010 - International Biometric Performance Testing Conference
The conference aimed to identify the important and new performance metrics and to expose best practice for evaluation. New performance results are not themselves in scope - instead the intention was to capture recent and best practice, to contrast that with the past, and to expose what is needed in the future. The overarching goal was to refine the concept of biometric performance and to ultimately elevate adoption and effectiveness of biometric technologies.
07-08 November 2007: Biometric Quality Workshop II
The workshop aimed at improving accuracy of biometric systems by incorporating quality assessment technologies into the sample acquisition process. It aimed to assess current quality measurement capabilities and to identify technologies, factors, operational paradigms, and standards that can measurably improve quality.
08-09 March 2006: Biometric Quality Workshop I
The workshop aimed at improving performance of biometric systems. It aimed to assess current quality measurement capabilities and to identify technologies, factors, operational paradigms, and standards that can measurably improve quality.
12 June 2013: IREX V: Guidance for Iris Image Collection
Guidance for the proper collection of iris images
24 September 2011: Iris Quality Calibration and Evaluation (IQCE): Evaluation Report
NIST Iris Quality Calibration and Evaluation (IQCE) was the first public challenge in iris image quality aimed at identifying iris image quality components that are algorithm- or camera-agnostic.
03 May 2007: Quality Summarization, Recommendations on Biometric Quality Summarization across the Application Domain
Provides technical guidance for users of biometric quality algorithms in large-scale enterprise operations.
14 April 2004: Fingerprint Image Quality
NFIQ's key innovation is to produce a quality value from a fingerprint image that is directly predictive of expected matching performance. Source code for the algorithm is included in the NBIS distribution.