Forensic Face Matching

Abstract

Person identification at passport control, at borders, in police investigations, and in criminal trials relies critically on the identity verification of people via image-to-image or person-to-image comparison. While this task is known as ‘facial image comparison’ in forensic settings, it has been studied as ‘unfamiliar face matching’ in cognitive science. This book brings together expertise from practitioners, and academics in psychology and law, to draw together what is currently known about these tasks. It explains the problem of identity impostors and how within-person variability and between-person similarity, due to factors such as image quality, lighting direction, and view, affect identification. A framework to develop a cognitive theory of face matching is offered. The face-matching abilities of untrained lay observers, facial reviewers, facial examiners, and super-recognizers are analysed and contrasted. Individual differences between observers, learning and training for face recognition and face matching, and personnel selection are reviewed. The admissibility criteria of evidence from face matching in legal settings are considered, focusing on aspects such as the requirement of relevance, the prohibition on evidence of opinion, and reliability. Key concepts relevant to automatic face recognition algorithms at airports and in police investigations are explained, such as deep convolutional neural networks, biometrics, and human–computer interaction. Finally, new security threats in the form of hyper-realistic mask disguises are considered, including the impact these have on person identification in applied and laboratory settings.