FRVT 2006 and ICE 2006 large-scale results

By P. J. Phillips, W. T. Scruggs, Alice J. O'Toole, Patrick J. Flynn, W. Kevin, Bowyer, Cathy L. Schott, Matthew Sharpe. 2007

373 citations recorded by the source corpus.

This report describes the large-scale experimental results from the Face Recognition Vendor Test (FRVT) 2006 and the Iris Challenge Evaluation (ICE) 2006. The FRVT 2006 looks at recognition from high-resolution still images and three-dimensional (3D) face images, and measures performance for still images taken under controlled and uncontrolled illumination. The ICE 2006 reports iris recognition performance from left and right iris images. The FRVT 2006 results from controlled still images and 3D images document an order-of-magnitude improvement in recognition performance over the FRVT 2002. This order-of-magnitude improvement was one of the goals of the preceding technology development effort, the Face Recognition Grand Challenge (FRGC). The FRVT 2006 and the ICE 2006 compared recognition performance from very-high resolution still face images, 3D face images, and single-iris images. On the FRVT 2006 and the ICE 2006 datasets, recognition performance was comparable for all three biometrics. In an experiment comparing human and algorithm performance, the best-performing face recognition algorithms were more accurate than humans. These and other results are discussed in detail. ∗Please direct correspondence to P. Jonathon Phillips at jonathon@nist.gov. We acknowledge the support of Department of Homeland Security’s Science and Technology Department and Transportation Security Administration (TSA), the Director of National Intelligence’s Information Technology Innovation Center, the Federal Bureau of Investigation (FBI), the National Institute of Justice, and the Technical Support Working Group (TSWG). The identification of any commercial product or trade name does not imply endorsement or recommendation by the National Institute of Standards and Technology, SAIC, Schafer Corp., U. of Texas at Dallas or U. of Notre Dame. 1

Subfields: Biomedical Engineering, Industrial and Manufacturing Engineering, Signal Processing

View Paper: https://www.semanticscholar.org/paper/50e77028e17155fe94322166028c23f935a55c9a

Citations in the corpus

• Biometric Template Security (2008, neutral): “Iris ICE 2006 [11] Controlled illumination, broad-quality range 1.”
• A Database and Evaluation Methodology for Optical Flow (2007, neutral): “Many areas of computer vision, such as stereo [19], face recognition [17], and object recognition [8], have challenging datasets to track the progress made by leading algorithms and to stimulate new ideas.”
• Handbook of Face Recognition, 2nd Edition (2011, neutral): “Plans for Australian identity cards were rejected because of just such fears and there was a significant backlash when retired Admiral John Poindexter conceived the “Total Information Awareness” (TIA) project [40] which aimed to gather and mine large quantities of data, of all kinds, and use these t”
• The Big Brother Database: Evaluating Face Recognition in Smart Home Environments (2009, neutral): “The results of recent evaluations [12] prove that state-of-the-art algorithms perform well in controlled environments but still poorly work in the presence of critical conditions.”
• Autotagging Facebook: Social network context improves photo annotation (2008, neutral): “[14, 15, 16]).”
• Toward a Practical Face Recognition System: Robust Alignment and Illumination by Sparse Representation (2012, neutral): “, [42].”
• Effective face frontalization in unconstrained images (2014, neutral): “Face recognition performances, reported as far back as [23], have shown computer vision capabilities to sur-† pass those of humans.”
• Effective Unconstrained Face Recognition by Combining Multiple Descriptors and Learned Background Statistics (2011, neutral): “…Challenge (FRGC) facial images and depths, along with accompanying benchmark tests [9], [10], and its successor, the Face Recognition Vendor Test (FRVT) database and benchmark [11], the CMU Pose Illumination and Expression (CMU-PIE) database [12], and its extension, the multi-PIE database [13].”