A k-NN Classification based VR User Verification using Eye Movement and Ocular Biomechanics

Publication Type:
Conference Proceeding
2019 IEEE International Conference on Systems, Man and Cybernetics (SMC), 2019, 2019-October, pp. 1844-1848
Issue Date:
Filename Description Size
08914577.pdfPublished version1.18 MB
Adobe PDF
Full metadata record
VR user identification is of utmost importance especially with the increased applications of VR that will include e-payment among other applications that requires a high level of security. Biometric identification through eye movement, has been used previously due to the intrinsic characteristics of eye movement that characterises a person uniquely. In this paper, we propose using eye movement along with extraocular muscle activations in VR user verification. The muscle activations are calculated using an ocular biomechanical model. The k-NN classification results showed approximately 90% accuracy when using a feature set with eye movement parameters (3 joint angles), muscle activations for all 6 muscles along with the VR object position in 3D. The classifier is a biometric VR user verification tool that provides an easy and non-intrusive methods that can be easily integrated in different VR applications that require user verification.
Please use this identifier to cite or link to this item: