Automated face recognition in forensic science: Review and perspectives

Abstract

With recent technological innovations, the multiplication of captured images of criminal events has brought the comparison of faces to the forefront of the judicial scene. Forensic face recognition has become a ubiquitous tool to guide investigations, gather intelligence and provide evidence in court. However, its reliability in court still suffers from the lack of methodological standardization and empirical validation, notably when using automatic systems, which compare images and generate a matching score. Although the use of such systems increases drastically, it still requires more empirical studies based on adequate forensic data (surveillance footages and identity documents) to become a reliable method to present evidence in court. In this paper, we propose a review of the literature leading to the establishment of a methodological workflow to develop a score-based likelihood-ratio computation model using a Bayesian framework. Different approaches are proposed in the literature regarding the within-source and between-source variability distributions modelling. Depending on the data available, the modelling approach can be specific to the case or generic. Generic approaches allow interpreting the score without any available images of the suspect. Such model is henceforth harder to defend in court because the results are not anchored to the suspect. To make sure the computed scorebased LR is robust, we must assess the performance of the model with two main characteristics: the discriminating power and the calibration state of the model. We hence describe the main metrics (Equal Error Rate and Cost of log likelihood-ratio), and graphical representations (Tippett plots, Detection Error Trade-off plot and Empirical Cross-Entropy plot) used to quantify and visualize the performance characteristics.

In search of a Goldilocks zone for credible AI

“…Take for example the medical application of image classifying AI 6 – 9 , or the forensic application of face recognition AI 16 —where there is currently evidence that optimal recognition involves collaboration between AI and human experts 67 . In each context, informational influence may be formed as decisions provided by AI combine with practitioners’ expert knowledge in cases/crimes varying in severity or risk.…”

“…Whereas, other semi or partially autonomous applications mimic specific human faculties, providing particular forms of knowledge or insight that, prior to modern developments in AI, were only available via interactions with other people. At present, perhaps the most societally important of these involve diagnostic classification of medical images by AI 6 – 9 , and the use of facial recognition AI for forensic or surveillance purposes 16 . Underwriting these applications is the use of image recognition and classification to support inferences about depicted persons, objects or events, with varying degrees of accuracy and bias.…”

Research on Fast Face Recognition Method Based on Double Decision Subspace

“…In the process of face recognition, expression changes will have a great impact on the recognition results. Overcoming expression changes is an important research content of face rapid recognition [30]. Among them, the mouth area is most affected by the change of expression.…”

Forensic face recognition based on KDE and evidence theory

“…But these methods need to be manually carried out by forensic experts, so they heavily depend on the experience and knowledge of the forensic experts. On the other hand, the objectivebased methods attempt to identify faces using automatic face recognition [6][7][8][9][10]. Using automatic recognition system to verify faces can not only improve the efficiency of forensic work, but also promote the standardization of the forensic process.…”