Deep neural network and data augmentation methodology for off-axis iris segmentation in wearable headsets
MetadataShow full item record
This item's downloads: 63 (view details)
Cited 12 times in Scopus (view citations)
Varkarakis, Viktor, Bazrafkan, Shabab, & Corcoran, Peter. (2020). Deep neural network and data augmentation methodology for off-axis iris segmentation in wearable headsets. Neural Networks, 121, 101-121. doi:10.1016/j.neunet.2019.07.020
A data augmentation methodology is presented and applied to generate a large dataset of off-axis iris regions and train a low-complexity deep neural network. Although of low complexity the resulting network achieves a high level of accuracy in iris region segmentation for challenging off-axis eye-patches. Interestingly, this network is also shown to achieve high levels of performance for regular, frontal, segmentation of iris regions, comparing favourably with state-of-the-art techniques of significantly higher complexity. Due to its lower complexity this network is well suited for deployment in embedded applications such as augmented and mixed reality headsets. (C) 2019 Elsevier Ltd. All rights reserved.