Cargando…
Highly Robust and Wearable Facial Expression Recognition via Deep-Learning-Assisted, Soft Epidermal Electronics
The facial expressions are a mirror of the elusive emotion hidden in the mind, and thus, capturing expressions is a crucial way of merging the inward world and virtual world. However, typical facial expression recognition (FER) systems are restricted by environments where faces must be clearly seen...
Autores principales: | , , , , , , , , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
AAAS
2021
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8302843/ https://www.ncbi.nlm.nih.gov/pubmed/34368767 http://dx.doi.org/10.34133/2021/9759601 |
_version_ | 1783726957233438720 |
---|---|
author | Zhuang, Meiqi Yin, Lang Wang, Youhua Bai, Yunzhao Zhan, Jian Hou, Chao Yin, Liting Xu, Zhangyu Tan, Xiaohui Huang, YongAn |
author_facet | Zhuang, Meiqi Yin, Lang Wang, Youhua Bai, Yunzhao Zhan, Jian Hou, Chao Yin, Liting Xu, Zhangyu Tan, Xiaohui Huang, YongAn |
author_sort | Zhuang, Meiqi |
collection | PubMed |
description | The facial expressions are a mirror of the elusive emotion hidden in the mind, and thus, capturing expressions is a crucial way of merging the inward world and virtual world. However, typical facial expression recognition (FER) systems are restricted by environments where faces must be clearly seen for computer vision, or rigid devices that are not suitable for the time-dynamic, curvilinear faces. Here, we present a robust, highly wearable FER system that is based on deep-learning-assisted, soft epidermal electronics. The epidermal electronics that can fully conform on faces enable high-fidelity biosignal acquisition without hindering spontaneous facial expressions, releasing the constraint of movement, space, and light. The deep learning method can significantly enhance the recognition accuracy of facial expression types and intensities based on a small sample. The proposed wearable FER system is superior for wide applicability and high accuracy. The FER system is suitable for the individual and shows essential robustness to different light, occlusion, and various face poses. It is totally different from but complementary to the computer vision technology that is merely suitable for simultaneous FER of multiple individuals in a specific place. This wearable FER system is successfully applied to human-avatar emotion interaction and verbal communication disambiguation in a real-life environment, enabling promising human-computer interaction applications. |
format | Online Article Text |
id | pubmed-8302843 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2021 |
publisher | AAAS |
record_format | MEDLINE/PubMed |
spelling | pubmed-83028432021-08-05 Highly Robust and Wearable Facial Expression Recognition via Deep-Learning-Assisted, Soft Epidermal Electronics Zhuang, Meiqi Yin, Lang Wang, Youhua Bai, Yunzhao Zhan, Jian Hou, Chao Yin, Liting Xu, Zhangyu Tan, Xiaohui Huang, YongAn Research (Wash D C) Research Article The facial expressions are a mirror of the elusive emotion hidden in the mind, and thus, capturing expressions is a crucial way of merging the inward world and virtual world. However, typical facial expression recognition (FER) systems are restricted by environments where faces must be clearly seen for computer vision, or rigid devices that are not suitable for the time-dynamic, curvilinear faces. Here, we present a robust, highly wearable FER system that is based on deep-learning-assisted, soft epidermal electronics. The epidermal electronics that can fully conform on faces enable high-fidelity biosignal acquisition without hindering spontaneous facial expressions, releasing the constraint of movement, space, and light. The deep learning method can significantly enhance the recognition accuracy of facial expression types and intensities based on a small sample. The proposed wearable FER system is superior for wide applicability and high accuracy. The FER system is suitable for the individual and shows essential robustness to different light, occlusion, and various face poses. It is totally different from but complementary to the computer vision technology that is merely suitable for simultaneous FER of multiple individuals in a specific place. This wearable FER system is successfully applied to human-avatar emotion interaction and verbal communication disambiguation in a real-life environment, enabling promising human-computer interaction applications. AAAS 2021-07-15 /pmc/articles/PMC8302843/ /pubmed/34368767 http://dx.doi.org/10.34133/2021/9759601 Text en Copyright © 2021 Meiqi Zhuang et al. https://creativecommons.org/licenses/by/4.0/Exclusive Licensee Science and Technology Review Publishing House. Distributed under a Creative Commons Attribution License (CC BY 4.0). |
spellingShingle | Research Article Zhuang, Meiqi Yin, Lang Wang, Youhua Bai, Yunzhao Zhan, Jian Hou, Chao Yin, Liting Xu, Zhangyu Tan, Xiaohui Huang, YongAn Highly Robust and Wearable Facial Expression Recognition via Deep-Learning-Assisted, Soft Epidermal Electronics |
title | Highly Robust and Wearable Facial Expression Recognition via Deep-Learning-Assisted, Soft Epidermal Electronics |
title_full | Highly Robust and Wearable Facial Expression Recognition via Deep-Learning-Assisted, Soft Epidermal Electronics |
title_fullStr | Highly Robust and Wearable Facial Expression Recognition via Deep-Learning-Assisted, Soft Epidermal Electronics |
title_full_unstemmed | Highly Robust and Wearable Facial Expression Recognition via Deep-Learning-Assisted, Soft Epidermal Electronics |
title_short | Highly Robust and Wearable Facial Expression Recognition via Deep-Learning-Assisted, Soft Epidermal Electronics |
title_sort | highly robust and wearable facial expression recognition via deep-learning-assisted, soft epidermal electronics |
topic | Research Article |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8302843/ https://www.ncbi.nlm.nih.gov/pubmed/34368767 http://dx.doi.org/10.34133/2021/9759601 |
work_keys_str_mv | AT zhuangmeiqi highlyrobustandwearablefacialexpressionrecognitionviadeeplearningassistedsoftepidermalelectronics AT yinlang highlyrobustandwearablefacialexpressionrecognitionviadeeplearningassistedsoftepidermalelectronics AT wangyouhua highlyrobustandwearablefacialexpressionrecognitionviadeeplearningassistedsoftepidermalelectronics AT baiyunzhao highlyrobustandwearablefacialexpressionrecognitionviadeeplearningassistedsoftepidermalelectronics AT zhanjian highlyrobustandwearablefacialexpressionrecognitionviadeeplearningassistedsoftepidermalelectronics AT houchao highlyrobustandwearablefacialexpressionrecognitionviadeeplearningassistedsoftepidermalelectronics AT yinliting highlyrobustandwearablefacialexpressionrecognitionviadeeplearningassistedsoftepidermalelectronics AT xuzhangyu highlyrobustandwearablefacialexpressionrecognitionviadeeplearningassistedsoftepidermalelectronics AT tanxiaohui highlyrobustandwearablefacialexpressionrecognitionviadeeplearningassistedsoftepidermalelectronics AT huangyongan highlyrobustandwearablefacialexpressionrecognitionviadeeplearningassistedsoftepidermalelectronics |