Deep Neural Network and Data Augmentation Methodology for off-axis iris segmentation in wearable headsets

TL;DR

This paper introduces a data augmentation approach and a low-complexity deep neural network for off-axis iris segmentation, achieving high accuracy suitable for embedded AR/VR headset applications.

Contribution

It presents a novel data augmentation methodology and a lightweight neural network that performs well in off-axis iris segmentation, comparable to more complex models.

Findings

High accuracy in off-axis iris segmentation

Effective performance on regular frontal iris images

Suitable for embedded AR/VR devices

Abstract

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.