Related Experiment Video
Updated: Feb 8, 2026

Foreign Accent and Forensic Speaker Identification in Voice Lineups: The Influence of Acoustic Features Based on Prosody
Published on: September 27, 2024
Forensic Odontology: Automatic Identification of Persons Comparing Antemortem and Postmortem Panoramic Radiographs
Andreas Heinrich1, Felix Güttler1, Sebastian Wendt1
1Department of Radiology, Jena University Hospital - Friedrich Schiller University, Jena, Germany.
This study introduces an automated system using computer vision to compare antemortem and postmortem panoramic radiographs for reliable person identification. The method efficiently matches dental records in large datasets, even with altered characteristics.
Area of Science:
- Forensic Odontology
- Computer Vision
- Radiographic Analysis
Background:
- Comparison of antemortem and postmortem panoramic radiographs (PRs) is a reliable method for person identification in forensic odontology.
- Automating this comparison process can improve efficiency and accuracy.
Purpose of the Study:
- To enhance and automate the identification of unknown individuals by comparing antemortem and postmortem PRs using computer vision.
- To develop a reliable and fast method for person identification from radiographic data.
Main Methods:
- Utilized a dataset of 43,467 PRs from 24,545 patients.
- Employed Matlab R2014b with image processing and computer vision toolboxes.
- Implemented the SURF feature for matching corresponding points between PRs in a large database.
Main Results:
- Achieved reliable identification for 85% (34 out of 40) of randomly selected persons.
- Identified a threshold of 12 matching points for reliable assignment between different PRs of the same person.
- Demonstrated robustness in matching, with up to 259 points for identical PRs and a maximum of 12 for non-identical ones.
Conclusions:
- An automated PR system with computer vision is a successful and reliable tool for forensic identification.
- The method offers fast and reliable identification, suitable for large datasets ('big data').
- The system remains effective even when dental characteristics have been altered (removed or added).
Related Concept Videos
Automatic Processing and Automatic Social Behavior
Vision
Color Vision
Depth Perception and Spatial Vision
Comparing Copy Number Variations and SNPs
Copy number variations or CNVs are the structural variations that cover more than 1kb of DNA sequence. The single nucleotide polymorphism (SNP), on the other hand, is a single nucleotide change or a point mutation that is found in more than 1%...
Personal Identity

