Forensic Facial Comparison: Current Status, Limitations, and Future Directions

Abstract

Global escalation of crime has necessitated the use of digital imagery to aid the identification of perpetrators. Forensic facial comparison (FFC) is increasingly employed, often relying on poor-quality images. In the absence of standardized criteria, especially in terms of video recordings, verification of the methodology is needed. This paper addresses aspects of FFC, discussing relevant terminology, investigating the validity and reliability of the FISWG morphological feature list using a new South African database, and advising on standards for CCTV equipment. Suboptimal conditions, including poor resolution, unfavorable angle of incidence, color, and lighting, affected the accuracy of FFC. Morphological analysis of photographs, standard CCTV, and eye-level CCTV showed improved performance in a strict iteration analysis, but not when using analogue CCTV images. Therefore, both strict and lenient iterations should be conducted, but FFC must be abandoned when a strict iteration performs worse than a lenient one. This threshold ought to be applied to the specific CCTV equipment to determine its utility. Chance-corrected accuracy was the most representative measure of accuracy, as opposed to the commonly used hit rate. While the use of automated systems is increasing, trained human observer-based morphological analysis, using the FISWG feature list and an Analysis, Comparison, Evaluation, and Verification (ACE-V) approach, should be the primary method of facial comparison.

Global adoption of facial recognition technology with special reference to India—Present status and future recommendations

“…The primary goal of forensic facial identification is to authenticate a target's identity and potential affiliation with a criminal event using photographic or video evidence of the target's face. 11 CCTV footage is utilized in crime prevention and law enforcement to safeguard and improve public security. 12 Images of offenders captured in surveillance are considered evidence in the court of the law.…”

Focus distance estimation from photographed faces: a test of PerspectiveX using 1709 frontal and profile photographs from DSLR and smartphone cameras

“…For example, facial photographs may be used to identify perpetrators of crime(s) [ 3 ], or to identify victims of crime and decedents [ 4 , 5 ]. In the former context, forensic facial comparison [ 6 – 9 ] and automated facial recognition [ 10 – 12 ] see frequent use. For decedent identification, facial photographs are often employed to evaluate the anatomical fit of a skull to a known face using a method known as craniofacial superimposition [ 13 – 30 ].…”

“…The automated facial recognition field has also encountered challenges dealing with FD, and without viable perspective correction methods in this field, it has been recommend that automated recognition systems should be trained on photographs taken from a range of distances [ 48 ]. In forensic facial comparison, a paucity of published methods to specifically address perspective distortions has also been recognised [ 6 ]. In this field, assessors are reported to qualitatively assess perspective distortion during their image analysis [ 6 ]—a highly subjective approach that may vary between practitioners.…”

“…In forensic facial comparison, a paucity of published methods to specifically address perspective distortions has also been recognised [ 6 ]. In this field, assessors are reported to qualitatively assess perspective distortion during their image analysis [ 6 ]—a highly subjective approach that may vary between practitioners.…”

Recent Advances in Forensic Anthropological Methods and Research

“…A topic with increasing attention is forensic facial comparison, which is the subject of one paper by Bacci and coworkers that discusses relevant terminology, the validity as well as reliability of the Facial Identification Scientific Working Group’s list of morphological features, and proposes standards for CCTV equipment [ 9 ].…”