A facial expression recognition network using hybrid feature extraction.

Facial expression recognition faces great challenges due to factors such as face similarity, image quality, and age variation. Although various existing end-to-end Convolutional Neural Network (CNN) architectures have achieved good classification results in facial expression recognition tasks, these...

Full description

Saved in:
Bibliographic Details
Main Authors: Dandan Song, Chao Liu
Format: Article
Language:English
Published: Public Library of Science (PLoS) 2025-01-01
Series:PLoS ONE
Online Access:https://doi.org/10.1371/journal.pone.0312359
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849314734944288768
author Dandan Song
Chao Liu
author_facet Dandan Song
Chao Liu
author_sort Dandan Song
collection DOAJ
description Facial expression recognition faces great challenges due to factors such as face similarity, image quality, and age variation. Although various existing end-to-end Convolutional Neural Network (CNN) architectures have achieved good classification results in facial expression recognition tasks, these network architectures share a common drawback that the convolutional kernel can only compute the correlation between elements of a localized region when extracting expression features from an image. This leads to difficulties for the network to explore the relationship between all the elements that make up a complete expression. In response to this issue, this article proposes a facial expression recognition network called HFE-Net. In order to capture the subtle changes of expression features and the whole facial expression information at the same time, HFE-Net proposed a Hybrid Feature Extraction Block. Specifically, Hybrid Feature Extraction Block consists of parallel Feature Fusion Device and Multi-head Self-attention. Among them, Feature Fusion Device not only extracts the local information in expression features, but also measures the correlation between distant elements in expression features, which helps the network to focus more on the target region while realizing the information interaction between distant features. And Multi-head Self-attention can calculate the correlation between the overall elements in the feature map, which helps the network to extract the overall information of the expression features. We conducted a lot of experiments on four publicly available facial expression datasets and verified that the Hybrid Feature Extraction Block constructed in this paper can improve the network's recognition ability for facial expressions.
format Article
id doaj-art-e6524466f2564ed6a463314493da6521
institution Kabale University
issn 1932-6203
language English
publishDate 2025-01-01
publisher Public Library of Science (PLoS)
record_format Article
series PLoS ONE
spelling doaj-art-e6524466f2564ed6a463314493da65212025-08-20T03:52:20ZengPublic Library of Science (PLoS)PLoS ONE1932-62032025-01-01201e031235910.1371/journal.pone.0312359A facial expression recognition network using hybrid feature extraction.Dandan SongChao LiuFacial expression recognition faces great challenges due to factors such as face similarity, image quality, and age variation. Although various existing end-to-end Convolutional Neural Network (CNN) architectures have achieved good classification results in facial expression recognition tasks, these network architectures share a common drawback that the convolutional kernel can only compute the correlation between elements of a localized region when extracting expression features from an image. This leads to difficulties for the network to explore the relationship between all the elements that make up a complete expression. In response to this issue, this article proposes a facial expression recognition network called HFE-Net. In order to capture the subtle changes of expression features and the whole facial expression information at the same time, HFE-Net proposed a Hybrid Feature Extraction Block. Specifically, Hybrid Feature Extraction Block consists of parallel Feature Fusion Device and Multi-head Self-attention. Among them, Feature Fusion Device not only extracts the local information in expression features, but also measures the correlation between distant elements in expression features, which helps the network to focus more on the target region while realizing the information interaction between distant features. And Multi-head Self-attention can calculate the correlation between the overall elements in the feature map, which helps the network to extract the overall information of the expression features. We conducted a lot of experiments on four publicly available facial expression datasets and verified that the Hybrid Feature Extraction Block constructed in this paper can improve the network's recognition ability for facial expressions.https://doi.org/10.1371/journal.pone.0312359
spellingShingle Dandan Song
Chao Liu
A facial expression recognition network using hybrid feature extraction.
PLoS ONE
title A facial expression recognition network using hybrid feature extraction.
title_full A facial expression recognition network using hybrid feature extraction.
title_fullStr A facial expression recognition network using hybrid feature extraction.
title_full_unstemmed A facial expression recognition network using hybrid feature extraction.
title_short A facial expression recognition network using hybrid feature extraction.
title_sort facial expression recognition network using hybrid feature extraction
url https://doi.org/10.1371/journal.pone.0312359
work_keys_str_mv AT dandansong afacialexpressionrecognitionnetworkusinghybridfeatureextraction
AT chaoliu afacialexpressionrecognitionnetworkusinghybridfeatureextraction
AT dandansong facialexpressionrecognitionnetworkusinghybridfeatureextraction
AT chaoliu facialexpressionrecognitionnetworkusinghybridfeatureextraction