A Novel Evolutionary Method for Automated Skull-Face Overlay in Computer-Aided Craniofacial Superimposition

TL;DR

This paper presents Lilium, an automated evolutionary approach that improves skull-face overlay accuracy in forensic identification by modeling soft-tissue variability and enforcing anatomical constraints.

Contribution

Lilium introduces a novel 3D cone-based soft-tissue model optimized with Differential Evolution for enhanced accuracy and robustness in craniofacial superimposition.

Findings

Lilium outperforms existing methods in accuracy.

Lilium demonstrates increased robustness against soft-tissue variability.

The method effectively enforces anatomical and photographic constraints.

Abstract

Craniofacial Superimposition is a forensic technique for identifying skeletal remains by comparing a post-mortem skull with ante-mortem facial photographs. A critical step in this process is Skull-Face Overlay (SFO). This stage involves aligning a 3D skull model with a 2D facial image, typically guided by cranial and facial landmarks' correspondence. However, its accuracy is undermined by individual variability in soft-tissue thickness, introducing significant uncertainty into the overlay. This paper introduces Lilium, an automated evolutionary method to enhance the accuracy and robustness of SFO. Lilium explicitly models soft-tissue variability using a 3D cone-based representation whose parameters are optimized via a Differential Evolution algorithm. The method enforces anatomical, morphological, and photographic plausibility through a combination of constraints: landmark matching, camera parameter consistency, head pose alignment, skull containment within facial boundaries, and region parallelism. This emulation of the usual forensic practitioners' approach leads Lilium to outperform the state-of-the-art method in terms of both accuracy and robustness.