Problem
Research questions and friction points this paper is trying to address.
post-mortem iris recognition
data collection
forensic biometrics
iris recognition
post-mortem interval
Beyond Mortality: Advancements in Post-Mortem Iris Recognition through Data Collection and Computer-Aided Forensic Examination
🤖 AI Summary
This study addresses the challenges of postmortem iris recognition, including data scarcity, inadequate algorithmic adaptation, and identity spoofing risks, by constructing the largest postmortem iris dataset to date—comprising 259 deceased subjects with postmortem intervals up to 1,674 hours—and releasing, for the first time, paired ante- and postmortem iris images from the same individuals. Near-infrared and visible-light images were captured in compliance with ISO/IEC 19794-6 standards. Evaluating five state-of-the-art iris recognition algorithms, the work reframes postmortem iris recognition as a presentation attack detection task, develops a dedicated detection model, and integrates explainable AI mechanisms. The authors further release an open-source forensic iris comparison tool that fuses three postmortem recognition strategies, demonstrating its efficacy on a cohort of 338 deceased subjects and significantly enhancing reliability and practicality in forensic applications.
📝 Abstract
Post-mortem iris recognition brings both hope to the forensic community (a short-term but accurate and fast means of verifying identity) as well as concerns to society (its potential illicit use in post-mortem impersonation). These hopes and concerns have grown along with the volume of research in post-mortem iris recognition. Barriers to further progress in post-mortem iris recognition include the difficult nature of data collection, and the resulting small number of approaches designed specifically for comparing iris images of deceased subjects. This paper makes several unique contributions to mitigate these barriers. First, we have collected and we offer a new dataset of NIR (compliant with ISO/IEC 19794-6 where possible) and visible-light iris images collected after demise from 259 subjects, with the largest PMI (post-mortem interval) being 1,674 hours. For one subject, the data has been collected before and after death, the first such case ever published. Second, the collected dataset was combined with publicly-available post-mortem samples to assess the current state of the art in automatic forensic iris recognition with five iris recognition methods and data originating from 338 deceased subjects. These experiments include analyses of how selected demographic factors influence recognition performance. Thirdly, this study implements a model for detecting post-mortem iris images, which can be considered as presentation attacks. Finally, we offer an open-source forensic tool integrating three post-mortem iris recognition methods with explainability elements added to make the comparison process more human-interpretable.
Innovation
Methods, ideas, or system contributions that make the work stand out.
post-mortem iris recognition
biometric dataset
presentation attack detection
forensic biometrics
explainable AI
🔎 Similar Papers
No similar papers found.
