The presentations from the IBPC 2012 conference are now available.
The final program for the conference is now available here. The program has evolved to include talks from 45 speakers from 11 countries on 4 continents, including representatives of 6 governments.
The main IBPC 2012 conference will be accompanied by two half-day satellite workshops on Monday March 5 and Friday March 9. On March 5th there will be a workshop on "Technical update on the second generation NIST Fingerprint Image Quality (NFIQ 2.0) Algorithm" . On March 9th there will be two workshops, one on "Artefact, Liveness, Suspicious Presentation Detection" and the other will be "Voice Biometrics Data Standardization for Law Enforcement, Military and Homeland Security".
The first draft of the full conference program and the satellite workshops is available here. Important: The registration deadline for international attendees is February 26.
The main IBPC 2012 conference will be accompanied by two half-day satellite workshops on Monday March 5 and Friday March 9. The focus of these sessions will be announced shortly.
The IBPC 2012 call for papers seeks abstracts for papers and presentations addressing biometric performance, measurement and specification. All aspects of performance of biometrics systems are in scope. These range from design, through human interaction, quality control, and algorithmic functions, to system assurance and summarization. Abstracts could be 1-5 pages long, preferably in PDF format. These should be emailed to the organizers at the following email: ibpc2012 [at] nist.gov (ibpc2012[at]nist[dot]gov). The conference is open to all parties, including members of the testing community, core technology providers, system builders, end-users, and operators. Of particular interest are presentations addressing novel testing techniques and metrics, operational performance realization, and gaps between operational need and test capability.
Important Dates:
In cooperation with the National Physical Laboratory and Fraunhofer IGD, NIST is pleased to announce, as the sequel to the IBPC 2010, an international forum for the discussion of recent advances in the fields of biometric testing, performance definition and specification, and assurance. The conference aims to identify fundamental, relevant, effective, and new performance metrics and to expose best practices for performance evaluation, calibration and design. New performance results are not themselves in scope - instead the intention is to capture relevant and recent quantitative testing, measurement and system-identification techniques to contrast those with the past, and to outline what is needed in the future. The overarching goal is to refine the concept of biometric performance and to ultimately elevate adoption and effectiveness of biometric technologies.
In the context of multifactor authentication, biometrics fill the role of the something-you-are and their utility rests on the correct analog-to-digital conversion to the particular human characteristic or trait. This is multi-disciplinary in nature and involves biological aspects, human factors, physical sensor technologies, computer vision and signal detection functions, and preparation of compressed, standardized, and viable samples. Thereafter, the algorithmic challenges leading to correct recognition exploit advances in image and signal processing, machine learning, pattern recognition and classification. These steps are often non-trivial and are potential sources of error. Therefore, biometric system performance is in general subject to tradeoffs between sample acceptance at one stage and rejection at a later one.
Prior NIST workshops, in 2006 and 2007, used the term "quality" as a proxy for performance. The goals of those forums was to distinguish quality-by-design from quality-by-practice, and to identify measureable quantities that predict recognition outcome. The 2010 and 2012 International Biometrics Performance Conferences have a broader scope: quantification of all factors that influence performance of the biometric system.