FCR: Investigating Generative AI models for Forensic Craniofacial Reconstruction

TL;DR

This paper introduces a novel framework using generative AI models to reconstruct faces from 2D X-ray images for forensic identification, demonstrating promising results in generating realistic faces and aiding forensic investigations.

Contribution

It is the first to utilize 2D X-ray images with generative models for craniofacial reconstruction, improving realism and potential forensic application.

Findings

Generated faces scored well on FID, IS, SSIM metrics.

The retrieval framework effectively matches reconstructed faces to real ones.

Proposed method offers a new tool for forensic identification.

Abstract

Craniofacial reconstruction in forensics is one of the processes to identify victims of crime and natural disasters. Identifying an individual from their remains plays a crucial role when all other identification methods fail. Traditional methods for this task, such as clay-based craniofacial reconstruction, require expert domain knowledge and are a time-consuming process. At the same time, other probabilistic generative models like the statistical shape model or the Basel face model fail to capture the skull and face cross-domain attributes. Looking at these limitations, we propose a generic framework for craniofacial reconstruction from 2D X-ray images. Here, we used various generative models (i.e., CycleGANs, cGANs, etc) and fine-tune the generator and discriminator parts to generate more realistic images in two distinct domains, which are the skull and face of an individual. This is the first time where 2D X-rays are being used as a representation of the skull by generative models for craniofacial reconstruction. We have evaluated the quality of generated faces using FID, IS, and SSIM scores. Finally, we have proposed a retrieval framework where the query is the generated face image and the gallery is the database of real faces. By experimental results, we have found that this can be an effective tool for forensic science.