Post-Mortem Iris Recognition Resistant to Biological Eye Decay Processes
This addresses the problem of reliable iris biometrics in forensics for identifying deceased individuals, representing a novel application rather than an incremental improvement.
The paper tackles iris recognition for post-mortem samples by developing an end-to-end method that fine-tunes a CNN-based segmentation model with diversified iris data and combines Gabor kernels with iris-specific kernels learned by Siamese networks, resulting in significant outperformance over existing methods on a new post-mortem iris image database for all time horizons since death.
This paper proposes an end-to-end iris recognition method designed specifically for post-mortem samples, and thus serving as a perfect application for iris biometrics in forensics. To our knowledge, it is the first method specific for verification of iris samples acquired after demise. We have fine-tuned a convolutional neural network-based segmentation model with a large set of diversified iris data (including post-mortem and diseased eyes), and combined Gabor kernels with newly designed, iris-specific kernels learnt by Siamese networks. The resulting method significantly outperforms the existing off-the-shelf iris recognition methods (both academic and commercial) on the newly collected database of post-mortem iris images and for all available time horizons since death. We make all models and the method itself available along with this paper.