EmojiHeroVR: A Study on Facial Expression Recognition under Partial Occlusion from Head-Mounted Displays

TL;DR

This study introduces EmoHeVRDB, a new facial expression database collected during VR gameplay with HMD occlusion, and evaluates the feasibility of facial emotion recognition under such conditions using deep learning.

Contribution

We created EmoHeVRDB, a comprehensive facial expression dataset under HMD occlusion, and provided baseline FER results demonstrating the challenge and potential of emotion recognition in VR environments.

Findings

Achieved 69.84% accuracy on static FER with deep learning.

Facial expression recognition under HMD occlusion is feasible but more challenging.

The dataset includes dynamic frames and facial activation data for future research.

Abstract

Emotion recognition promotes the evaluation and enhancement of Virtual Reality (VR) experiences by providing emotional feedback and enabling advanced personalization. However, facial expressions are rarely used to recognize users' emotions, as Head-Mounted Displays (HMDs) occlude the upper half of the face. To address this issue, we conducted a study with 37 participants who played our novel affective VR game EmojiHeroVR. The collected database, EmoHeVRDB (EmojiHeroVR Database), includes 3,556 labeled facial images of 1,778 reenacted emotions. For each labeled image, we also provide 29 additional frames recorded directly before and after the labeled image to facilitate dynamic Facial Expression Recognition (FER). Additionally, EmoHeVRDB includes data on the activations of 63 facial expressions captured via the Meta Quest Pro VR headset for each frame. Leveraging our database, we conducted a baseline evaluation on the static FER classification task with six basic emotions and neutral using the EfficientNet-B0 architecture. The best model achieved an accuracy of 69.84% on the test set, indicating that FER under HMD occlusion is feasible but significantly more challenging than conventional FER.