Recognizability of Demographically Altered Computerized Facial Approximations in an Automated Facial Recognition Context for Potential Application in Unidentified Persons Data Repositories

SIMPLE SUMMARY: Forensic anthropologists are tasked with estimating a “biological profile” from bones. This profile includes potentially individualizing characteristics, including sex, age, ancestry, and stature. If only a skull is found and the facial bony structure is intact, its biological profile can be used by a forensic artist or with computer software to construct a facial approximation, which is an informed estimate of how the person may have looked in life. The facial approximation is then released to the public and to other agencies, and facial recognition software may be used to search the approximation against images of missing persons. In case the biological profile is inaccurate due to incomplete or damaged skeletal remains, it is sometimes useful to construct additional facial approximations that are based on alternative sex and ancestry characteristics, especially for use with facial recognition software. This research found that alternative sex facial approximations, when searched against a large gallery of facial photographs, produced higher match scores than did alternative ancestry facial approximations. ABSTRACT: This study examined the recognizability of demographically altered facial approximations for potential utility in unidentified persons tracking systems. Five computer-generated approximations were generated for each of 26 African male participants using the following demographic parameters: (i) African male (true demographics), (ii) African female, (iii) Caucasian male, (iv) Asian male, and (v) Hispanic male. Overall, 62% of the true demographic facial approximations for the 26 African male participants examined were matched to a corresponding life photo within the top 50 images of a candidate list generated from an automated blind search of an optimally standardized gallery of 6159 photographs. When the African male participants were processed as African females, the identification rate was 50%. In contrast, less congruent identification rates were observed when the African male participants were processed as Caucasian (42%), Asian (35%), and Hispanic (27%) males. The observed results suggest that approximations generated using the opposite sex may be operationally informative if sex is unknown. The performance of approximations generated using alternative ancestry assignments, however, was less congruent with the performance of the true demographic approximation (African male) and may not yield as operationally constructive data as sex-altered approximations.