Forensic Iris Image Synthesis

Post-mortem iris recognition is an emerging application of iris-based human identification in a forensic setup, able to correctly identify deceased subjects even three weeks post-mortem. This technique thus is considered as an important component of future forensic toolkits. The current advancements in this field are seriously slowed down by exceptionally difficult data collection, which can happen in mortuary conditions, at crime scenes, or in “body farm” facilities. This paper makes a novel contribution to facilitate progress in post-mortem iris recognition by offering a conditional StyleGAN-based iris synthesis model, trained on the largest-available dataset of post-mortem iris samples acquired from more than 350 subjects, generating – through appropriate exploration of StyleGAN latent space – multiple within-class (same identity) and between-class (different new identities) post-mortem iris images, compliant with ISO/IEC 29794-6, and with decomposition deformations controlled by the requested PMI (post mortem interval). Besides an obvious application to enhance the existing, very sparse, post-mortem iris datasets to advance – among others – iris presentation attack endeavors, we anticipate it may be useful to generate samples that would expose professional forensic human examiners to never-seen-before deformations for various PMIs, increasing their training effectiveness. The source codes and model weights are made available with the paper.

1. Introduction

The immeasurable appetite of modern machine learning for data is unfading, despite a success of various few-shot and transfer learning approaches. This is especially true in emerging domains, in which we are just discovering the domain's specificity, often solely through sparse and insuf-ficient data. Post-mortem iris recognition is one of such domains. It gains more attention, however, after discov-ery that it may be considered in forensic applications [1], and after seeing the first post-mortem-specific and human-interpretable recognition methods being proposed [2], [3]. Al-though it sounds gruesome, it also constitutes yet another presentation attack type, and receives an attention in the pre-sentation attack detection area.