U.S. flag

An official website of the United States government, Department of Justice.

NCJRS Virtual Library

The Virtual Library houses over 235,000 criminal justice resources, including all known OJP works.
Click here to search the NCJRS Virtual Library

Facial Recognition: Assessing Its Viability in the Corrections Environment

NCJ Number
189646
Journal
Corrections Today Volume: 63 Issue: 4 Dated: July 2001 Pages: 62-64
Author(s)
Mike Bone; Carl Crumbacker
Date Published
July 2001
Length
3 pages
Annotation
This article provides an overview of FRVT 2000 (Facial Recognition Vendor Test), which established performance criteria for facial recognition systems for particular applications, and discusses follow-up efforts that will evaluate the feasibility of facial recognition in a correctional environment.
Abstract
FRVT 2000 used a three-step evaluation protocol: a top-level technology evaluation followed by a scenario evaluation and an operational evaluation. The FRVT 2000 performed a technology evaluation titled "Recognition Performance Test" and a limited scenario evaluation titled "Product Usability Test." For the Recognition Performance Test, vendors were given 13,872 images and were asked to compare each image to all the other images (more than 192 million comparisons). These data were used to develop experiments that showed how well the systems responded to numerous variables such as pose, lighting, and image compression level. The product usability tests consisted of two timed tests, which were used to measure the response time of the overall system for two different access-control scenarios. Results from FRVT 2000 showed mixed conclusions regarding the viability of facial recognition for the correctional environment. Based on results from the technology evaluation and limited scenario evaluation, an operational evaluation is being developed at a correctional facility in Prince George's County, MD. There are two goals for this first-phase evaluation and demonstration. The first is to provide technology that will increase the safety of correctional officers. This is being provided by the access-control system and its logging capabilities to determine which employees are within the facility at a given time. The second goal is to familiarize employees with facial recognition technology and to determine how well these employees can interface with the facial recognition system. Future phases will be determined based on results from this evaluation. 1 reference