NCJ Number
219972
Journal
Law Enforcement Technology Volume: 34 Issue: 7 Dated: July 2007 Pages: 32,34,40
Date Published
July 2007
Length
8 pages
Annotation
This article describes computerized technologies for determining whether separate facial images are of the same person.
Abstract
Computerized facial-recognition systems, which usually consist of a camera teamed with software on a computer linked to a central database, perform automated comparisons of facial images based on unique features of the face. The facial features used by the algorithm vary among suppliers, but they typically are ones that do not change significantly over time due to differences in facial hair, glasses, or aging. The products can be used on photographs as well as live still images and video images. There are two kinds of facial recognition systems. One is two-dimensional. It takes a digital photo and measures points on a face, such as the base of the nose to the edge of the right eye. These systems work well if the camera that records the image is directly in front of the person. The other system is three-dimensional. It measures facial shapes, contours, the width of the nose, and depth of the eyes for up to 20,000 points. ALIVE Tech, Inc. offers both types of systems. Although most law enforcement departments have a two-dimensional database of mugshots, ALIVE Tech recommends three-dimensional systems for most law enforcement applications, so as to widen the options for matching photos taken of a person's face from various angles. This is likely to occur in attempting to match facial images from surveillance photos and videos. This article identifies both the benefits of facial recognition in law enforcement and its potential drawbacks. One of the drawbacks is its lack of 100-percent reliability in making matches. Corroboration from other evidence sources is necessary for conclusive identifications.