Iris Reflection Segmentation from Ocular Images Acquired in Uncontrolled and Uncooperative Conditions
Contributo in Atti di convegno
Data di Pubblicazione:
2023
Citazione:
Iris Reflection Segmentation from Ocular Images Acquired in Uncontrolled and Uncooperative Conditions / R. Donida Labati, V. Piuri, F. Rundo, F. Scotti (... IEEE INTERNATIONAL CONFERENCE ON COMPUTATIONAL INTELLIGENCE AND VIRTUAL ENVIRONMENTS FOR MEASUREMENT SYSTEMS AND APPLICATIONS). - In: 2023 IEEE International Conference on Computational Intelligence and Virtual Environments for Measurement Systems and Applications (CIVEMSA)[s.l] : IEEE, 2023. - ISBN 979-8-3503-3636-8. - pp. 1-6 (( convegno CIVEMSA tenutosi a Gammarth nel 2023 [10.1109/CIVEMSA57781.2023.10231007].
Abstract:
The segmentation of reflections from the iris region
is a relevant task for biometric systems, human-machine inter-
action technologies, and photo editing applications. This task
is particularly complex for ocular images acquired from unco-
operative users in uncontrolled illumination and environmental
conditions. Furthermore, to the best of our knowledge, all of the
studies in the literature on methods specifically designed to detect
reflections in the iris texture are based on algorithmic approaches.
In this paper, we present the first study on deep neural networks
for segmenting reflection regions from iris images. Specifically,
we propose a modified version of the U-Net architecture based
on an encoder (downsampler) characterized by a relatively low
computational complexity, and designed with the aim of being
applied on edge devices. Experiments have been performed for a
dataset of 3,286 ocular images acquired from websites and social
media in completely uncontrolled and uncooperative conditions.
The obtained results prove that our proposed method can
accurately segment the iris reflections for particularly challenging
images. A detailed qualitative analysis also confirm the robustness
of our method for non-ideal application contexts. Furthermore,
experiments show that our method can increase the accuracy
of state-of-the-art iris segmentation techniques based on deep
neural networks.
Tipologia IRIS:
03 - Contributo in volume
Keywords:
Reflections; iris; segmentation; deep learning; edge computing; biometrics
Elenco autori:
R. Donida Labati, V. Piuri, F. Rundo, F. Scotti
Link alla scheda completa:
Titolo del libro:
2023 IEEE International Conference on Computational Intelligence and Virtual Environments for Measurement Systems and Applications (CIVEMSA)