Post-mortem iris recognition is an emerging application of iris-based human identification in a forensic setup. One factor that may be useful in conditioning iris recognition methods is the tissue decomposition level, which is correlated with the post-mortem interval (PMI), \ie the number of hours that have elapsed since death. PMI, however, is not always available, and its precise estimation remains one of the core challenges in forensic examination. This paper presents the first known to us method of the PMI estimation directly from iris images captured after death. To assess the feasibility of the iris-based PMI estimation, we designed models predicting the PMI from (a) near-infrared (NIR), (b) visible (RGB), and (c) multispectral (RGB+NIR) forensic iris images. Models were evaluated following a 10-fold cross-validation, in (S1) sample-disjoint, (S2) subject-disjoint, and (S3) cross-dataset scenarios. We explore two data balancing techniques for S3: resampling-based balancing (S3-real), and synthetic data-supplemented balancing (S3-synthetic). We found that using the multispectral data offers a spectacularly low mean absolute error (MAE) of $\approx 3.5$ hours in the scenario (S1), a bit worse MAE $\approx 17.5$ hours in the scenario (S2), and MAE $\approx 45.77$ hours in the scenario (S3). Additionally, supplementing the training set with synthetically-generated forensic iris images (S3-synthetic) significantly enhances the models' ability to generalize to new NIR, RGB and multispectral data collected in a different lab. This suggests that if the environmental conditions are favorable (\eg, bodies are kept in low temperatures), forensic iris images provide features that are indicative of the PMI and can be automatically estimated.

翻译：死后虹膜识别是虹膜身份识别在法医学领域的一种新兴应用。影响虹膜识别方法的一个可能因素是组织分解程度，这与死后间隔（PMI），即自死亡后经过的小时数相关。然而，PMI并非总是已知，其精确估计仍然是法医检验的核心挑战之一。本文提出了我们已知的首个直接从死后采集的虹膜图像估计PMI的方法。为了评估基于虹膜的PMI估计的可行性，我们设计了从以下图像预测PMI的模型：(a) 近红外（NIR）、(b) 可见光（RGB）以及 (c) 多光谱（RGB+NIR）法医虹膜图像。模型在以下三种场景中采用10折交叉验证进行评估：(S1) 样本独立、(S2) 受试者独立以及 (S3) 跨数据集场景。我们探索了两种用于S3场景的数据平衡技术：基于重采样的平衡（S3-real）和合成数据补充的平衡（S3-synthetic）。我们发现，使用多光谱数据在场景(S1)中取得了极低的平均绝对误差（MAE）$\approx 3.5$小时，在场景(S2)中MAE稍差，为$\approx 17.5$小时，在场景(S3)中MAE为$\approx 45.77$小时。此外，用合成生成的法医虹膜图像（S3-synthetic）补充训练集，显著增强了模型对不同实验室采集的新NIR、RGB和多光谱数据的泛化能力。这表明，如果环境条件有利（例如，尸体保存在低温下），法医虹膜图像能够提供指示PMI的特征，并且可以进行自动估计。