Over the last couple of years, face recognition researchers have been developing new techniques, such as recognition from three-dimensional and high resolution imagery. These developments are being fueled by advances in computer vision techniques, computer design, sensor design, and interest in fielding face recognition systems. These techniques hold the promise of reducing the error rate in face recognition systems by an order of magnitude over FRVT 2002 results. The Face Recognition Grand Challenge (FRGC) is designed to achieve this performance goal by making available to researchers a data corpus of 50,000 images and a challenge problem containing six experiments. The data consists of 3D scans and high resolution still imagery. The imagery is taken under controlled and uncontrolled conditions. This paper describes the data corpus and challenge problems, and presents baseline performance and preliminary results on natural statistics of facial imagery.
Proceedings Title: IEEE Computer Society International Conference on Computer Vision and Pattern Recognition
Conference Dates: June 20-25, 2005
Conference Location: san diego, CA
Pub Type: Conferences
biometrics, evaluation, face recognition