Facial recognition technology (FRT) has emerged as an attractive solution to address many contemporary needs foridentication and the verication of identity claims. It brings together the promise of other biometric systems, whichattempt to tie identity to individually distinctive features of the body, and the more familiar functionality of visualsurveillance systems. This report develops a socio-political analysis that bridges the technical and social-scienticliteratures on FRT and addresses the unique challenges and concerns that attend its development, evaluation, andspecic operational uses, contexts, and goals. It highlights the potential and limitations of the technology, noting thosetasks for which it seems ready for deployment, those areas where performance obstacles may be overcome by futuretechnological developments or sound operating procedures, and still other issues which appear intractable. Its concern with efcacy extends to ethical considerations.For the purposes of this summary, the main ndings and recommendations of the report are broken down into vebroad categories: performance, evaluation, operation, policy concerns, and moral and political considerations. Thesendings and recommendations employ certain technical concepts and language that are explained and explored in thebody of the report and glossary, to which you should turn for further elaboration.
: What types of tasks can current FRT successfully perform, and under what conditions? What are theknown limitations on performance?FRT has proven effective, with relatively small populations in controlled environments, for the vericationa.of identity claims, in which an image of an individual’s face is matched to a pre-existing image “on-le”associated with the claimed identity (the verication task). FRT performs rather poorly in more complexattempts to identify individuals who do not voluntarily self-identify, in which the FRT seeks to match anindividual’s face with any possible image “on-le”
(the identication task). Specically, the “face in thecrowd” scenario, in which a face is picked out from a crowd in an uncontrolled environment, is unlikely to become an operational reality for the foreseeable future.FRT can only recognize a face if a specic individual’s face has already been added to (enrolled in)b.the system in advance. The conditions of enrollment—voluntary or otherwise—and the quality of theresulting image (the gallery image) have signicant impact on the nal efcacy of FRT. Image quality ismore signicant than any other single factor in the overall performance of FRT.If certain existing standards for images (ANSI INCITS 385-2004 and ISO/IEC 19794-5:2005) are metc.or exceeded, most of the current, top-performing FRT could well deliver a high level of accuracy forthe verication task. Given that images at the site of verication or identication (the probe image) areoften captured on low quality video, meeting these standards is no small feat, and has yet to be achievedin practice.Performance is also contingent on a number of other known factors, the most signicant of which are:d.
: The more similar the environments of the images to be compared (background,lighting conditions, camera distance, and thus the size and orientation of the head), the better theFRT will perform.
: The less time that has elapsed between the images to be compared, the better the FRT will perform.
Consistent Camera Use
: The more similar the optical characteristics of the camera used for theenrollment process and for obtaining the on-site image (light intensity, focal length, color balance,etc.), the better the FRT will perform.
: Given that the number of possible images that enter the gallery as near-identicalmathematical representations (biometric doubles) increases as the size of the gallery increases,restricting the size of the gallery in “open set” identication applications (such as watch listapplications) may help maintain the integrity of the system and increase overall performance.