Facial Expression Recognition based on Convolutional Neural Network with Sparse Representation
Facial Expression Recognition (FER) in the wild using Convolutional Neural Networks (CNNs) has been a challenge for years because of the significant intra-class variances and interclass similarities. In contrast, facial expression recognition in the wild is vital for human-computer interactions and...
Uložené v:
| Vydané v: | 2022 8th International Conference on Systems and Informatics (ICSAI) s. 1 - 6 |
|---|---|
| Hlavní autori: | , , |
| Médium: | Konferenčný príspevok.. |
| Jazyk: | English |
| Vydavateľské údaje: |
IEEE
10.12.2022
|
| Predmet: | |
| On-line prístup: | Získať plný text |
| Tagy: |
Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
|
| Abstract | Facial Expression Recognition (FER) in the wild using Convolutional Neural Networks (CNNs) has been a challenge for years because of the significant intra-class variances and interclass similarities. In contrast, facial expression recognition in the wild is vital for human-computer interactions and has numerous applications. Enhancing the discriminative features extraction ability is one approach to solving this issue. In this work, a sparse transform is used to improve a CNN's ability to extract features without adding to the network's computational load. We use a sparse representation layer that is built by the Haar wavelet transform or shearlet transform prior to the convolutional layers of a standard CNN. With the proposed sparse representation layers, we introduce a VGGNet and an AlexNet architecture and conduct experiments on the FER2013 dataset without the use of additional training data. The experimental results demonstrated that the wavelet transform's sparse representation layer can improve FER performance without increasing an excessive computational burden. We achieved testing accuracy of 73.25 percent on the FER2013 dataset using VGGNet paired with a sparse representation layer built inside a wavelet transform, which is among the best results for a single network. |
|---|---|
| AbstractList | Facial Expression Recognition (FER) in the wild using Convolutional Neural Networks (CNNs) has been a challenge for years because of the significant intra-class variances and interclass similarities. In contrast, facial expression recognition in the wild is vital for human-computer interactions and has numerous applications. Enhancing the discriminative features extraction ability is one approach to solving this issue. In this work, a sparse transform is used to improve a CNN's ability to extract features without adding to the network's computational load. We use a sparse representation layer that is built by the Haar wavelet transform or shearlet transform prior to the convolutional layers of a standard CNN. With the proposed sparse representation layers, we introduce a VGGNet and an AlexNet architecture and conduct experiments on the FER2013 dataset without the use of additional training data. The experimental results demonstrated that the wavelet transform's sparse representation layer can improve FER performance without increasing an excessive computational burden. We achieved testing accuracy of 73.25 percent on the FER2013 dataset using VGGNet paired with a sparse representation layer built inside a wavelet transform, which is among the best results for a single network. |
| Author | Liu, Xuan Ma, Jiachen Wang, Qiang |
| Author_xml | – sequence: 1 givenname: Xuan surname: Liu fullname: Liu, Xuan email: hitliuxuan@163.com organization: Harbin Institute of Technology,Department of Control Science and Engineering,Harbin,PR China – sequence: 2 givenname: Jiachen surname: Ma fullname: Ma, Jiachen email: hitmjc@163.com organization: Harbin Institute of Technology,Department of Control Science and Engineering,Weihai,PR China – sequence: 3 givenname: Qiang surname: Wang fullname: Wang, Qiang email: wangqiang@hit.edu.cn organization: Harbin Institute of Technology,Department of Control Science and Engineering,Harbin,PR China |
| BookMark | eNo1j8tOwzAURI0EC1r4Axb-gQTf-JF4WUUtRKpAol1TOfENWAQ7clIKf0_CYzWj0ZmRZkHOffBICAWWAjB9W5W7VSVzAJ1mLMtSYIxJUcAZWYBSUuRCFPySPG9M40xH1599xGFwwdMnbMKLd-PsazOgpZMpg_8I3XEOJ_oBj_FHxlOIb_Tkxle6600ccGrPQ-hHM7NX5KI13YDXf7ok-816X94n28e7qlxtEyd0kUjINULLleIarChQq0YYC9pIaFmrZaPzos6ZBMOsMspazYXizEqR6RqAL8nN76xDxEMf3buJX4f_y_wbimtSHA |
| ContentType | Conference Proceeding |
| DBID | 6IE 6IL CBEJK RIE RIL |
| DOI | 10.1109/ICSAI57119.2022.10005481 |
| DatabaseName | IEEE Electronic Library (IEL) Conference Proceedings IEEE Xplore POP ALL IEEE Xplore All Conference Proceedings IEEE Electronic Library (IEL) IEEE Proceedings Order Plans (POP All) 1998-Present |
| DatabaseTitleList | |
| Database_xml | – sequence: 1 dbid: RIE name: IEEE Xplore url: https://ieeexplore.ieee.org/ sourceTypes: Publisher |
| DeliveryMethod | fulltext_linktorsrc |
| EISBN | 1665474483 9781665474481 |
| EndPage | 6 |
| ExternalDocumentID | 10005481 |
| Genre | orig-research |
| GrantInformation_xml | – fundername: National Natural Science Foundation of China funderid: 10.13039/501100001809 |
| GroupedDBID | 6IE 6IL CBEJK RIE RIL |
| ID | FETCH-LOGICAL-i498-5179e1f366391d48e96c4ad19a51f0f95c978b7051a0d6a6dd934630d5429b113 |
| IEDL.DBID | RIE |
| IngestDate | Thu Jan 18 11:14:50 EST 2024 |
| IsPeerReviewed | false |
| IsScholarly | false |
| Language | English |
| LinkModel | DirectLink |
| MergedId | FETCHMERGED-LOGICAL-i498-5179e1f366391d48e96c4ad19a51f0f95c978b7051a0d6a6dd934630d5429b113 |
| PageCount | 6 |
| ParticipantIDs | ieee_primary_10005481 |
| PublicationCentury | 2000 |
| PublicationDate | 2022-Dec.-10 |
| PublicationDateYYYYMMDD | 2022-12-10 |
| PublicationDate_xml | – month: 12 year: 2022 text: 2022-Dec.-10 day: 10 |
| PublicationDecade | 2020 |
| PublicationTitle | 2022 8th International Conference on Systems and Informatics (ICSAI) |
| PublicationTitleAbbrev | ICSAI |
| PublicationYear | 2022 |
| Publisher | IEEE |
| Publisher_xml | – name: IEEE |
| Score | 1.8163079 |
| Snippet | Facial Expression Recognition (FER) in the wild using Convolutional Neural Networks (CNNs) has been a challenge for years because of the significant... |
| SourceID | ieee |
| SourceType | Publisher |
| StartPage | 1 |
| SubjectTerms | Convolutional codes convolutional neural network Dictionaries Face recognition Facial expression recognition Feature extraction multilayer convolutional sparse coding sparse representation Training Training data Wavelet transforms |
| Title | Facial Expression Recognition based on Convolutional Neural Network with Sparse Representation |
| URI | https://ieeexplore.ieee.org/document/10005481 |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| link | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV07b8IwELZa1KFTW5Wqb2XoarCxE8djhUBlQagwMBU5vovEEhAF1J9fn0mKOnTo5JPl2NI50T3yfXeMvYjUebDOcJ0LxTUo4BbzkjvyfnsCgo9axGYTZjzO53M7qcnqkQuDiBF8hh0S4798WPkdpcq6MnoYRLQ-NcYcyFoNOkfY7qg_fR2lRkoioPR6nWb5r8Yp0W4ML_554iVrHxl4yeTHtlyxE6yu2cfQUYI7GXzV6NUqeW_wP0EmgwRJEMIe-_qNCqup_EYcIt47ocRrMl2HeBbD0-sj-6hqs9lwMOu_8bo_Al9qm3MqroWyVMFnsBJ0jjbz2oG0LpWlKG3qQ4RYmPDVuaBzlwFYpTMlgFpUFVKqG9aqVhXesqRAmYJy1mAIj5QSznqdgUOpvBIW_B1rk24W60MFjEWjlvs_5h_YOd0AwT6keGSt7WaHT-zM77fLz81zvLdvCTGbFQ |
| linkProvider | IEEE |
| linkToHtml | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LTwIxEG4MmuhJjRjf9uC10G67jx4NgUBEQoQDJ0m3M5twWQgC8efbll2NBw-eOmm2bTLdzTz2-2YIeeKxsaBNylTGJVMggWnMCma89xtxcD5qHppNpKNRNpvpcUVWD1wYRAzgM2x5MfzLh6Xd-lRZWwQPwxOtD2OlIrGna9X4HK7bg87keRCnQngKShS16gW_WqcEy9E7_eeZZ6T5w8Gj42_rck4OsLwg7z3jU9y0-1nhV0v6ViOAnOxNElAnuD121TvlnvYFOMIQEN_Up17pZOUiWnSrVz_8o7JJpr3utNNnVYcEtlA6Y768FopCOq9BC1AZ6sQqA0KbWBS80LF1MWKeuu_OOK2bBEBLlUgOvklVLoS8JI1yWeIVoTmKGKTRKboASUputFUJGBTSSq7BXpOm1818ta-BMa_VcvPH_CM57k9fh_PhYPRyS078bXgQiOB3pLFZb_GeHNndZvGxfgh3-AVIy55c |
| openUrl | ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Abook&rft.genre=proceeding&rft.title=2022+8th+International+Conference+on+Systems+and+Informatics+%28ICSAI%29&rft.atitle=Facial+Expression+Recognition+based+on+Convolutional+Neural+Network+with+Sparse+Representation&rft.au=Liu%2C+Xuan&rft.au=Ma%2C+Jiachen&rft.au=Wang%2C+Qiang&rft.date=2022-12-10&rft.pub=IEEE&rft.spage=1&rft.epage=6&rft_id=info:doi/10.1109%2FICSAI57119.2022.10005481&rft.externalDocID=10005481 |