Cargando…
Light-FER: A Lightweight Facial Emotion Recognition System on Edge Devices
Facial emotion recognition (FER) systems are imperative in recent advanced artificial intelligence (AI) applications to realize better human–computer interactions. Most deep learning-based FER systems have issues with low accuracy and high resource requirements, especially when deployed on edge devi...
Autores principales: | , , , , , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
MDPI
2022
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9738842/ https://www.ncbi.nlm.nih.gov/pubmed/36502225 http://dx.doi.org/10.3390/s22239524 |
_version_ | 1784847650546253824 |
---|---|
author | Pascual, Alexander M. Valverde, Erick C. Kim, Jeong-in Jeong, Jin-Woo Jung, Yuchul Kim, Sang-Ho Lim, Wansu |
author_facet | Pascual, Alexander M. Valverde, Erick C. Kim, Jeong-in Jeong, Jin-Woo Jung, Yuchul Kim, Sang-Ho Lim, Wansu |
author_sort | Pascual, Alexander M. |
collection | PubMed |
description | Facial emotion recognition (FER) systems are imperative in recent advanced artificial intelligence (AI) applications to realize better human–computer interactions. Most deep learning-based FER systems have issues with low accuracy and high resource requirements, especially when deployed on edge devices with limited computing resources and memory. To tackle these problems, a lightweight FER system, called Light-FER, is proposed in this paper, which is obtained from the Xception model through model compression. First, pruning is performed during the network training to remove the less important connections within the architecture of Xception. Second, the model is quantized to half-precision format, which could significantly reduce its memory consumption. Third, different deep learning compilers performing several advanced optimization techniques are benchmarked to further accelerate the inference speed of the FER system. Lastly, to experimentally demonstrate the objectives of the proposed system on edge devices, Light-FER is deployed on NVIDIA Jetson Nano. |
format | Online Article Text |
id | pubmed-9738842 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2022 |
publisher | MDPI |
record_format | MEDLINE/PubMed |
spelling | pubmed-97388422022-12-11 Light-FER: A Lightweight Facial Emotion Recognition System on Edge Devices Pascual, Alexander M. Valverde, Erick C. Kim, Jeong-in Jeong, Jin-Woo Jung, Yuchul Kim, Sang-Ho Lim, Wansu Sensors (Basel) Article Facial emotion recognition (FER) systems are imperative in recent advanced artificial intelligence (AI) applications to realize better human–computer interactions. Most deep learning-based FER systems have issues with low accuracy and high resource requirements, especially when deployed on edge devices with limited computing resources and memory. To tackle these problems, a lightweight FER system, called Light-FER, is proposed in this paper, which is obtained from the Xception model through model compression. First, pruning is performed during the network training to remove the less important connections within the architecture of Xception. Second, the model is quantized to half-precision format, which could significantly reduce its memory consumption. Third, different deep learning compilers performing several advanced optimization techniques are benchmarked to further accelerate the inference speed of the FER system. Lastly, to experimentally demonstrate the objectives of the proposed system on edge devices, Light-FER is deployed on NVIDIA Jetson Nano. MDPI 2022-12-06 /pmc/articles/PMC9738842/ /pubmed/36502225 http://dx.doi.org/10.3390/s22239524 Text en © 2022 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/). |
spellingShingle | Article Pascual, Alexander M. Valverde, Erick C. Kim, Jeong-in Jeong, Jin-Woo Jung, Yuchul Kim, Sang-Ho Lim, Wansu Light-FER: A Lightweight Facial Emotion Recognition System on Edge Devices |
title | Light-FER: A Lightweight Facial Emotion Recognition System on Edge Devices |
title_full | Light-FER: A Lightweight Facial Emotion Recognition System on Edge Devices |
title_fullStr | Light-FER: A Lightweight Facial Emotion Recognition System on Edge Devices |
title_full_unstemmed | Light-FER: A Lightweight Facial Emotion Recognition System on Edge Devices |
title_short | Light-FER: A Lightweight Facial Emotion Recognition System on Edge Devices |
title_sort | light-fer: a lightweight facial emotion recognition system on edge devices |
topic | Article |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9738842/ https://www.ncbi.nlm.nih.gov/pubmed/36502225 http://dx.doi.org/10.3390/s22239524 |
work_keys_str_mv | AT pascualalexanderm lightferalightweightfacialemotionrecognitionsystemonedgedevices AT valverdeerickc lightferalightweightfacialemotionrecognitionsystemonedgedevices AT kimjeongin lightferalightweightfacialemotionrecognitionsystemonedgedevices AT jeongjinwoo lightferalightweightfacialemotionrecognitionsystemonedgedevices AT jungyuchul lightferalightweightfacialemotionrecognitionsystemonedgedevices AT kimsangho lightferalightweightfacialemotionrecognitionsystemonedgedevices AT limwansu lightferalightweightfacialemotionrecognitionsystemonedgedevices |