Iris Image Segmentation under Troublesome Conditions

---

---

    Iris image segmentation is the first and the most critical element of iris recognition pipeline. It is known to be difficult to be reliably executed by conventional iris recognition methods, especially for iris images not compliant with ISO/IEC 19794-6, such as pictures of eyes with conditions, or post-mortem iris samples. In this project we explore various deep-learning architectures to offer new methods in iris segmentation for challenging cases.

---

Adam Czajka, Kevin Bowyer

Collaborators: Daniel Kerrigan, Mateusz Trokielewicz

Data-Driven Segmentation of Post-mortem Iris Images, Mateusz Trokielewicz, Adam Czajka, 6th IAPR/IEEE International Workshop on Biometrics and Forensics (IWBF 2018), June 7 - 8, 2018, Sassari, Italy: [pdf]