Date Published: February 13, 2019
Publisher: Public Library of Science
Author(s): Alice Towler, Richard I. Kemp, A. Mike Burton, James D. Dunn, Tanya Wayne, Reuben Moreton, David White, Marina A. Pavlova.
Facial image comparison practitioners compare images of unfamiliar faces and decide whether or not they show the same person. Given the importance of these decisions for national security and criminal investigations, practitioners attend training courses to improve their face identification ability. However, these courses have not been empirically validated so it is unknown if they improve accuracy. Here, we review the content of eleven professional training courses offered to staff at national security, police, intelligence, passport issuance, immigration and border control agencies around the world. All reviewed courses include basic training in facial anatomy and prescribe facial feature (or ‘morphological’) comparison. Next, we evaluate the effectiveness of four representative courses by comparing face identification accuracy before and after training in novices (n = 152) and practitioners (n = 236). We find very strong evidence that short (1-hour and half-day) professional training courses do not improve identification accuracy, despite 93% of trainees believing their performance had improved. We find some evidence of improvement in a 3-day training course designed to introduce trainees to the unique feature-by-feature comparison strategy used by facial examiners in forensic settings. However, observed improvements are small, inconsistent across tests, and training did not produce the qualitative changes associated with examiners’ expertise. Future research should test the benefits of longer examination-focussed training courses and incorporate longitudinal approaches to track improvements caused by mentoring and deliberate practice. In the absence of evidence that training is effective, we advise agencies to explore alternative evidence-based strategies for improving the accuracy of face identification decisions.
Critical identification procedures, such as passport checks at border control and identifying offenders from CCTV surveillance footage, require facial image comparison practitioners to verify the identity of unfamiliar people by comparing faces. Errors in these situations can have serious personal and societal consequences, such as convicting an innocent person while the true perpetrator goes free. By far the most common way to mitigate these risks is for practitioners to attend training courses to improve their ability . However, very little is known about this training. Official guidelines for the content of facial image comparison training courses exist (see [2, 3] and S1 Appendix), but it is unclear to what extent agencies adhere to them. More importantly, we do not know if professional training courses improve identification accuracy. Here, we report a comprehensive review of current professional facial image comparison training courses and report the first empirical evaluations of their effectiveness.
The Facial Identification Scientific Working Group (FISWG) develop best-practice guidelines for facial image comparison (see  and S1 Appendix). Membership comprises agencies across several countries, including the United States Federal Bureau of Investigation (FBI), Department of State, and Army; the Australian Federal Police, Passport Office, and Home Affairs; the UK Metropolitan Police Service and Home Office; and, the Netherlands Forensic Institute (NFI). FISWG’s training guidelines are available for agencies to use when developing training, and recommend that training includes: principles of comparison, automated biometric systems, image science, media, image processing, facial knowledge and legal issues.
We evaluated the effectiveness of four of the training courses reviewed above (Courses A, B, C & D) to determine if they improve identification accuracy. In each evaluation, we compared the training group/s to a control group of participants who received training unrelated to face identification. All evaluations employed a pre- to post-test design whereby participants completed a series of tests before and after training so that we could track changes in accuracy as a result of training. The pre- and post-tests always included the Glasgow Face Matching Test (GFMT; see Fig 2A; ), and other tests specifically designed to simulate the casework each training course is intended to improve. For all tests, we split items into two sets of equal difficulty using accuracy data from previous studies so that equivalent versions could be administered at pre- and post-test. In the following sections, we report only critical aspects of the design and procedure with full details provided in the Methods section.
This paper provides the first comprehensive evaluation of the effectiveness of professional facial image comparison training courses. In a rigorous review of training courses used by the international community, we found that training typically includes facial anatomy, feature comparison and photography (see Fig 1 and S2 Appendix). The courses evaluated here were representative of accepted practice in facial image comparison training, and so results are likely to be indicative of the effectiveness of professional training courses more generally.