EUVIMEDEUVIMED entdecken
Crossref

Evaluating match confidence in automated face recognition via likelihood ratio determination: A case study

Claudio Ciampini, Giuliano Iacobellis, Federico Zomparelli, Luca Vidoni

Journal of Forensic Sciences · 2025

DOI: 10.1111/1556-4029.70234 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Forensic Sciences, 2025. Verfasst von Claudio Ciampini und 3 weiteren Autor:innen. Beteiligte Einrichtung: Scientific Investigations Department of Parma, Carabinieri Scientific Investigation Group, Parma, Italy. Hauptthemen laut MEDLINE: Automated Facial Recognition. Die Arbeit nennt 34 Literaturangaben. Gefördert von: the European Union's Horizon 2020 research and innovation program.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Forensic facial examinations (FFE) primarily relies on manual image examination by trained experts using standardized protocols to identify suspects through detailed comparisons. In contrast, automated facial recognition (AFR) employs machine learning and AI algorithms to generate match scores between faces, producing ranked lists of potential suspects within a given population. In both these approaches, final identification decisions must still be validated and justified by qualified practitioners to ensure legal accountability and court admissibility. This study presents an innovative FFE workflow based on the output of AFR and empowered by the use of a Bayesian statistical software tool based on kernel density estimation (KDE) for likelihood ratio (LR) calculation, demonstrated through a case study conducted with the Carabinieri Investigation Department. The methodology is based on (1) the generation of match scores between facial images using automated software, (2) the calculation of LRs through statistical modeling against reference population data, (3) Tippett Plot validation aligned with ENFSI (European Network of Forensic Science Institutes) guidelines to demonstrate model accuracy to ensure forensic reliability beyond mere LR calculation. The proposed framework provides court‐admissible statistical results for facial comparisons while maintaining practitioner oversight. This methodological approach can support forensic practitioners in the courtroom with a statistical result related to the use of AFR tools. This methodology has been shared with ENFSI experts in facial comparison.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Automated Facial RecognitionHumansLikelihood FunctionsBayes TheoremSoftwareMachine LearningAlgorithmsImage Processing, Computer-Assisted

Stichwörter der Autor:innen

KDEautomated facial recognitionfacial comparisonforensic facial examinationslikelihood ratiovideo surveillance

Autor:innen und Institutionen

  • Scientific Investigations Department of Parma, Carabinieri Scientific Investigation Group, Parma, Italy.
  • Reseach and Development Department, Carabinieri Scientific Investigation Group, Rome, Italy.
  • Scientific Investigations Department of Rome, Carabinieri Scientific Investigation Group, Rome, Italy.
  • Information Technology Department, Carabinieri Scientific Investigation Group, Rome, Italy.

Förderung

  • the European Union's Horizon 2020 research and innovation program

Zitieren

APA

Ciampini, C., Iacobellis, G., Zomparelli, F., & Vidoni, L. (2025). Evaluating match confidence in automated face recognition via likelihood ratio determination: A case study. Journal of Forensic Sciences. https://doi.org/10.1111/1556-4029.70234

Vancouver

Ciampini C, Iacobellis G, Zomparelli F, Vidoni L. Evaluating match confidence in automated face recognition via likelihood ratio determination: A case study. Journal of Forensic Sciences. 2025. doi:10.1111/1556-4029.70234

BibTeX
@article{Ciampini2025,
  author = {Ciampini, Claudio and Iacobellis, Giuliano and Zomparelli, Federico and Vidoni, Luca},
  title = {Evaluating match confidence in automated face recognition via likelihood ratio determination: A case study},
  journal = {Journal of Forensic Sciences},
  year = {2025},
  doi = {10.1111/1556-4029.70234}
}
Kostenlos starten →