Deep Neural Network and Data Augmentation Methodology for off-axis iris segmentation in wearable headsets
This work addresses the problem of accurate iris segmentation in embedded applications like AR/MR headsets, though it is incremental as it builds on existing deep learning methods with a focus on efficiency.
The paper tackles off-axis iris segmentation for wearable headsets by developing a data augmentation method and a low-complexity deep neural network, achieving high accuracy in segmentation for both off-axis and frontal iris regions, with performance comparable to more complex state-of-the-art techniques.
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 favorably 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.