Segmenting images of the human eye is a critical step in several tasks like iris recognition, eye tracking or pupil tracking. There are a lot of well-established hand-crafted methods that have been used in commercial practice. However, with the advances in deep learning, several deep network approaches outperform the handcrafted methods. Many of the approaches adapt the U-Net architecture for the segmentation task. In this paper we propose some simple and effective new modifications of U-Net, e.g. the increase in size of convolutional kernels, which can improve the segmentation results compared to the original U-Net design. Using these modifications, we show that we can reach state-of-the-art performance using less model parameters. We describe our motivation for the changes in the architecture, inspired mostly by the hand-crafted methods and basic image processing principles and finally we show that our optimized model slightly outperforms the original U-Net and the other state-of-the-art models.
Sabry, SAM , Omelina, L , Cornelis, J & Jansen, B 2022, Iris Segmentation based on an Optimized U-Net . in BIOSIGNALS 2022. pp. 176-183. < https://www.scitepress.org/PublishedPapers/2022/108258/108258.pdf >
Sabry, S. A. M. , Omelina, L. , Cornelis, J. , & Jansen, B. (2022). Iris Segmentation based on an Optimized U-Net . In BIOSIGNALS 2022 (pp. 176-183) https://www.scitepress.org/PublishedPapers/2022/108258/108258.pdf
@inproceedings{327db1b083d94521bd4012793fb9ffd6,
title = " Iris Segmentation based on an Optimized U-Net " ,
abstract = " Segmenting images of the human eye is a critical step in several tasks like iris recognition, eye tracking or pupil tracking. There are a lot of well-established hand-crafted methods that have been used in commercial practice. However, with the advances in deep learning, several deep network approaches outperform the handcrafted methods. Many of the approaches adapt the U-Net architecture for the segmentation task. In this paper we propose some simple and effective new modifications of U-Net, e.g. the increase in size of convolutional kernels, which can improve the segmentation results compared to the original U-Net design. Using these modifications, we show that we can reach state-of-the-art performance using less model parameters. We describe our motivation for the changes in the architecture, inspired mostly by the hand-crafted methods and basic image processing principles and finally we show that our optimized model slightly outperforms the original U-Net and the other state-of-the-art models. " ,
author = " Sabry, {Sabry Abdalla M} and Lubos Omelina and Jan Cornelis and Bart Jansen " ,
year = " 2022 " ,
language = " English " ,
pages = " 176183 " ,
booktitle = " BIOSIGNALS 2022 " ,
}