FERET Evaluation Methodology for Face-Recognition Algorithms

摘要

Two of the most critical requirements in support of producing reliable face-211u001erecognition systems are a large database of facial images and a testing procedure 211u001eto evaluate systems. The Face Recognition Technology (FERET) program has 211u001eaddressed both issues through the FERET database of facial images and the 211u001eestablishment of the FERET tests. To date, 14,126 images from 1199 individuals 211u001eare included in the FERET database, which is divided into development and 211u001esequestered portions of the database. In September 1996, the FERET program 211u001eadministered the third in a series of FERET face-recognition tests. The primary 211u001eobjectives of the third test were to (1) assess the state of the art, (2) 211u001eidentify future areas of research, and (3) measure algorithm performance.