학술논문

Skeleton-ID: AI-driven Human Identification
Document Type
Conference
Source
2023 IEEE Conference on Artificial Intelligence (CAI) CAI Artificial Intelligence (CAI), 2023 IEEE Conference on. :278-279 Jun, 2023
Subject
Computing and Processing
General Topics for Engineers
Three-dimensional displays
Forensics
Image processing
DNA
X-rays
Fingerprint recognition
Software
forensic medicine
forensic anthropology
human identification
human rights
artificial intelligence
Language
Abstract
Victims of crime, migration, natural disasters, and armed conflicts often remain unidentified due to the absence of DNA samples and fingerprints. Skeleton-based identification (ID) methods could help to identify these victims because they are suitable for poorly preserved bodies and require comparison data that is relatively easy to obtain —e.g., a simple photo of the victim— instead of a DNA sample of a close relative or access to a database in another country. Skeleton-ID™ is a game-changing software designed for skeleton-based human identification using artificial intelligence (AI). Combining forensic anthropology and odontology methods with cutting-edge image processing and AI technologies allows us to apply these methods on a large scale. This leads to very high reliability (up to 99%), obtaining explainable results, and a drastic reduction of identification time (days to minutes). The software is accessible through a web browser and can process ante-mortem (AM) information on missing persons as well as post-mortem (PM) information. Usable data includes ordinary photos, 3D scans of bones, x-rays, and dental records.