Problem
Research questions and friction points this paper is trying to address.
virtual reality
iris recognition
unconstrained acquisition
biometric authentication
periocular recognition
Ocular Verification for Virtual Reality
🤖 AI Summary
This study addresses the performance degradation of iris recognition in virtual reality (VR) environments caused by unconstrained conditions such as off-axis gaze, uneven illumination, and specular reflections. It presents the first systematic analysis of the failure mechanisms of ISO/IEC 29794-6 iris quality metrics on VR data, revealing that certain criteria—such as edge completeness—are no longer applicable. To mitigate these degradations, the authors propose a generative model-based image enhancement approach and introduce both unimodal and score-level multimodal fusion strategies leveraging iris and periocular regions. Experimental results demonstrate that the proposed multimodal fusion scheme reduces the equal error rate (EER) by approximately 11% compared to unimodal iris recognition, significantly improving authentication accuracy in VR settings.
📝 Abstract
Virtual reality (VR) headsets (e.g., Meta Quest, Apple Vision Pro) provide a seamless user experience due to their fast, frictionless interaction with the physical world in a simulated environment. User authentication relies on biometric cues such as iris in such headsets. However, traditional iris recognition protocols may not be adequate in cases of unconstrained acquisition, which is typical of VR-based data. In this work, we examine three crucial aspects: (1) evaluating ISO/IEC 29794-6 iris quality metrics on VRBiom dataset and analyzing their limitations, (2) addressing data-specific challenges such as off-axis gaze, non-uniform illumination, and specular reflection using generative models, and (3) performing unimodal (iris, periocular) recognition and multimodal score-level fusion (iris + periocular). We observe that some metrics (e.g., margin adequacy) fail on VR-acquired data; whereas, image adjustments primarily benefit periocular recognition, and multimodal fusion lowers EER by ~11% over unimodal iris recognition performance. We will release the evaluation scripts upon acceptance for reproducibility.
Innovation
Methods, ideas, or system contributions that make the work stand out.
iris recognition
periocular recognition
generative models
multimodal fusion
virtual reality biometrics
🔎 Similar Papers
No similar papers found.
💼 Related Jobs
