Face expression recognition based on NGO-BILSTM model
IntroductionFacial expression recognition has always been a hot topic in computer vision and artificial intelligence. In recent years, deep learning models have achieved good results in accurately recognizing facial expressions. BILSTM network is such a model. However, the BILSTM network's perf...
Published in: | Frontiers in Neurorobotics |
---|---|
Main Authors: | , , |
Format: | Article in Journal/Newspaper |
Language: | English |
Published: |
Frontiers Media S.A.
2023
|
Subjects: | |
Online Access: | https://doi.org/10.3389/fnbot.2023.1155038 https://doaj.org/article/8b35182618904203ba8ae8d992f87fd4 |
id |
ftdoajarticles:oai:doaj.org/article:8b35182618904203ba8ae8d992f87fd4 |
---|---|
record_format |
openpolar |
spelling |
ftdoajarticles:oai:doaj.org/article:8b35182618904203ba8ae8d992f87fd4 2023-05-15T17:43:04+02:00 Face expression recognition based on NGO-BILSTM model Jiarui Zhong Tangxian Chen Liuhan Yi 2023-03-01T00:00:00Z https://doi.org/10.3389/fnbot.2023.1155038 https://doaj.org/article/8b35182618904203ba8ae8d992f87fd4 EN eng Frontiers Media S.A. https://www.frontiersin.org/articles/10.3389/fnbot.2023.1155038/full https://doaj.org/toc/1662-5218 1662-5218 doi:10.3389/fnbot.2023.1155038 https://doaj.org/article/8b35182618904203ba8ae8d992f87fd4 Frontiers in Neurorobotics, Vol 17 (2023) northern goshawk algorithm NGO-BILSTM model face recognition facial expression hyperparameter optimization Neurosciences. Biological psychiatry. Neuropsychiatry RC321-571 article 2023 ftdoajarticles https://doi.org/10.3389/fnbot.2023.1155038 2023-03-26T01:35:46Z IntroductionFacial expression recognition has always been a hot topic in computer vision and artificial intelligence. In recent years, deep learning models have achieved good results in accurately recognizing facial expressions. BILSTM network is such a model. However, the BILSTM network's performance depends largely on its hyperparameters, which is a challenge for optimization.MethodsIn this paper, a Northern Goshawk optimization (NGO) algorithm is proposed to optimize the hyperparameters of BILSTM network for facial expression recognition. The proposed methods were evaluated and compared with other methods on the FER2013, FERplus and RAF-DB datasets, taking into account factors such as cultural background, race and gender.ResultsThe results show that the recognition accuracy of the model on FER2013 and FERPlus data sets is much higher than that of the traditional VGG16 network. The recognition accuracy is 89.72% on the RAF-DB dataset, which is 5.45, 9.63, 7.36, and 3.18% higher than that of the proposed facial expression recognition algorithms DLP-CNN, gACNN, pACNN, and LDL-ALSG in recent 2 years, respectively.DiscussionIn conclusion, NGO algorithm effectively optimized the hyperparameters of BILSTM network, improved the performance of facial expression recognition, and provided a new method for the hyperparameter optimization of BILSTM network for facial expression recognition. Article in Journal/Newspaper Northern Goshawk Directory of Open Access Journals: DOAJ Articles Frontiers in Neurorobotics 17 |
institution |
Open Polar |
collection |
Directory of Open Access Journals: DOAJ Articles |
op_collection_id |
ftdoajarticles |
language |
English |
topic |
northern goshawk algorithm NGO-BILSTM model face recognition facial expression hyperparameter optimization Neurosciences. Biological psychiatry. Neuropsychiatry RC321-571 |
spellingShingle |
northern goshawk algorithm NGO-BILSTM model face recognition facial expression hyperparameter optimization Neurosciences. Biological psychiatry. Neuropsychiatry RC321-571 Jiarui Zhong Tangxian Chen Liuhan Yi Face expression recognition based on NGO-BILSTM model |
topic_facet |
northern goshawk algorithm NGO-BILSTM model face recognition facial expression hyperparameter optimization Neurosciences. Biological psychiatry. Neuropsychiatry RC321-571 |
description |
IntroductionFacial expression recognition has always been a hot topic in computer vision and artificial intelligence. In recent years, deep learning models have achieved good results in accurately recognizing facial expressions. BILSTM network is such a model. However, the BILSTM network's performance depends largely on its hyperparameters, which is a challenge for optimization.MethodsIn this paper, a Northern Goshawk optimization (NGO) algorithm is proposed to optimize the hyperparameters of BILSTM network for facial expression recognition. The proposed methods were evaluated and compared with other methods on the FER2013, FERplus and RAF-DB datasets, taking into account factors such as cultural background, race and gender.ResultsThe results show that the recognition accuracy of the model on FER2013 and FERPlus data sets is much higher than that of the traditional VGG16 network. The recognition accuracy is 89.72% on the RAF-DB dataset, which is 5.45, 9.63, 7.36, and 3.18% higher than that of the proposed facial expression recognition algorithms DLP-CNN, gACNN, pACNN, and LDL-ALSG in recent 2 years, respectively.DiscussionIn conclusion, NGO algorithm effectively optimized the hyperparameters of BILSTM network, improved the performance of facial expression recognition, and provided a new method for the hyperparameter optimization of BILSTM network for facial expression recognition. |
format |
Article in Journal/Newspaper |
author |
Jiarui Zhong Tangxian Chen Liuhan Yi |
author_facet |
Jiarui Zhong Tangxian Chen Liuhan Yi |
author_sort |
Jiarui Zhong |
title |
Face expression recognition based on NGO-BILSTM model |
title_short |
Face expression recognition based on NGO-BILSTM model |
title_full |
Face expression recognition based on NGO-BILSTM model |
title_fullStr |
Face expression recognition based on NGO-BILSTM model |
title_full_unstemmed |
Face expression recognition based on NGO-BILSTM model |
title_sort |
face expression recognition based on ngo-bilstm model |
publisher |
Frontiers Media S.A. |
publishDate |
2023 |
url |
https://doi.org/10.3389/fnbot.2023.1155038 https://doaj.org/article/8b35182618904203ba8ae8d992f87fd4 |
genre |
Northern Goshawk |
genre_facet |
Northern Goshawk |
op_source |
Frontiers in Neurorobotics, Vol 17 (2023) |
op_relation |
https://www.frontiersin.org/articles/10.3389/fnbot.2023.1155038/full https://doaj.org/toc/1662-5218 1662-5218 doi:10.3389/fnbot.2023.1155038 https://doaj.org/article/8b35182618904203ba8ae8d992f87fd4 |
op_doi |
https://doi.org/10.3389/fnbot.2023.1155038 |
container_title |
Frontiers in Neurorobotics |
container_volume |
17 |
_version_ |
1766145091328540672 |