Emotion Recognition in Gamers Wearing Head-mounted Display
Lists
Only you see this
Abstract
Wearing head-mounted display (HMD) makes previous research regarding emotion recognition using machine vision ineffective since they utilized entire face images for training. In this paper, we trained the convolutional neural networks (CNNs) which are capable of estimating the emotions from the images of a face wearing a HMD by hiding eyes and eyebrows from existing face-emotion dataset. Our analysis based on the class activation maps show that it is capable of classifying emotions without the eyes and the eyebrows which ar to serve useful information in recognizing emotions. This implies the possibility of estimating the emotions from the images of humans wearing HMDs using machine vision.
BibTeX
@inproceedings{yong2019emotion,
author = {Hwanmoo Yong and Jisuk Lee and Jongeun Choi},
title = {{Emotion Recognition in Gamers Wearing Head-mounted Display}},
booktitle = {Vr},
year = {2019},
doi = {10.1109/vr.2019.8797736},
}Loading related content...