Auto-Encoders Derivatives on Different Occluded Face Images: Comprehensive Review and New Results

This paper presents a novel approach for improving occluded face recognition performance using a family of autoencoders (AE) architectures. The proposed structures include four stages: image preprocessing, feature extraction using autoencoder derivatives, classification via a convolutional neural ne...

Celý popis

Uložené v:

Podrobná bibliografia
Vydané v:	IEEE access Ročník 13; s. 195080 - 195103
Hlavní autori:	Masoudi, Azin, Ahmadi, Majid
Médium:	Journal Article
Jazyk:	English
Vydavateľské údaje:	Piscataway IEEE 2025 The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Predmet:	Accuracy Artificial neural networks Autoencoders Coders Convolutional autoencoder Convolutional codes Convolutional neural networks Datasets Deep learning Deepfakes Face recognition Feature extraction Image reconstruction occluded dataset Occlusion Performance evaluation Robustness self-supervised autoencoder smooth autoencoder Transformers
ISSN:	2169-3536, 2169-3536
On-line prístup:	Získať plný text
Tagy:	Pridať tag Žiadne tagy, Buďte prvý, kto otaguje tento záznam!

Abstract	This paper presents a novel approach for improving occluded face recognition performance using a family of autoencoders (AE) architectures. The proposed structures include four stages: image preprocessing, feature extraction using autoencoder derivatives, classification via a convolutional neural network (CNN), and evaluation on occluded, non-occluded, and unseen datasets. Three deep autoencoder variants with combinational loss terms have been introduced to extract features from images: Convolutional Autoencoder (CAE), Self-Supervised Convolutional Autoencoder (SSCAE), and Smooth Convolutional Autoencoder (SCAE). A Masked Convolutional Autoencoder (MCAE) is also introduced to evaluate the capability of our convolutional autoencoder model in reconstructing images from masked inputs. Seven public datasets have been utilized to evaluate the performance of the proposed methods: the Extended Yale Dataset B, FERET, CMU Multi-PIE, Occluded ORL, Masked LFW (MLFW), AR, and RMFRD. Occluded ORL is used to analyze the performance of the proposed autoencoder derivatives on severely occluded images. MLFW is used to test the generalization of the proposed methods as an unseen dataset for the encoder part of the autoencoder variants. The recognition accuracies of 100% for FERET, 99.89% for the Extended Yale B, 99.45% for the CMU Multi-PIE, and 94.2% for unseen MLFW, and the ability to reconstruct masked ORL with 90% of masking, demonstrate that the proposed methods achieve significant improvement in accuracy for face recognition with acceptable computational cost in comparison to the state-of-the-art. To the best of our knowledge, this study is the first work where convolutional autoencoder architectures achieve such performance on occluded datasets without incorporating any occlusion-specific design.
AbstractList	This paper presents a novel approach for improving occluded face recognition performance using a family of autoencoders (AE) architectures. The proposed structures include four stages: image preprocessing, feature extraction using autoencoder derivatives, classification via a convolutional neural network (CNN), and evaluation on occluded, non-occluded, and unseen datasets. Three deep autoencoder variants with combinational loss terms have been introduced to extract features from images: Convolutional Autoencoder (CAE), Self-Supervised Convolutional Autoencoder (SSCAE), and Smooth Convolutional Autoencoder (SCAE). A Masked Convolutional Autoencoder (MCAE) is also introduced to evaluate the capability of our convolutional autoencoder model in reconstructing images from masked inputs. Seven public datasets have been utilized to evaluate the performance of the proposed methods: the Extended Yale Dataset B, FERET, CMU Multi-PIE, Occluded ORL, Masked LFW (MLFW), AR, and RMFRD. Occluded ORL is used to analyze the performance of the proposed autoencoder derivatives on severely occluded images. MLFW is used to test the generalization of the proposed methods as an unseen dataset for the encoder part of the autoencoder variants. The recognition accuracies of 100% for FERET, 99.89% for the Extended Yale B, 99.45% for the CMU Multi-PIE, and 94.2% for unseen MLFW, and the ability to reconstruct masked ORL with 90% of masking, demonstrate that the proposed methods achieve significant improvement in accuracy for face recognition with acceptable computational cost in comparison to the state-of-the-art. To the best of our knowledge, this study is the first work where convolutional autoencoder architectures achieve such performance on occluded datasets without incorporating any occlusion-specific design.
Author	Masoudi, Azin Ahmadi, Majid
Author_xml	– sequence: 1 givenname: Azin orcidid: 0009-0009-5629-2560 surname: Masoudi fullname: Masoudi, Azin email: masoudia@uwindsor.ca organization: Department of Electrical and Computer Engineering, University of Windsor, Windsor, ON, Canada – sequence: 2 givenname: Majid orcidid: 0000-0001-5781-6754 surname: Ahmadi fullname: Ahmadi, Majid organization: Department of Electrical and Computer Engineering, University of Windsor, Windsor, ON, Canada
BookMark	eNpNUdtOGzEQtRBIQOAL6IOlPif1ZX3rW7SENhICicuz5bVn6UbJOti7Qfx9TRe1nZcZHc05czTnHB33sQeErihZUErMt2Vdrx4fF4wwseCSMyrMETpjVJo5F1we_zefosucN6SULpBQZ8gtxyHOV72PAVLG15C6gxu6A2Qce3zdtS0k6Ad87_12DBDwjfOA1zv3Avk7ruNun-AX9Lkw8AMcOnjDrg_4rvQHyON2yBfopHXbDJeffYaeb1ZP9c_57f2Pdb28nXumij3qG8Ukb5gQmlQi6BYYATCaU2iElC01PkilAm88qIYIBZVX3mlinGiN4DO0nnRDdBu7T93OpXcbXWf_ADG9WJeGzm_Bai0daYSqtOdVJalpBKFUMt6a0HDNitbXSWuf4usIebCbOKa-2LecKW5kZcqnZ4hPWz7FnBO0f69SYj-isVM09iMa-xlNYX2ZWB0A_GNQVlFGDP8NQ_mKeg
CODEN	IAECCG
Cites_doi	10.1111/exsy.13625 10.1016/j.imavis.2009.08.002 10.3390/s25051574 10.1109/iccvw.2019.00322 10.3390/s20020342 10.3390/electronics14091736 10.1016/j.patcog.2023.110127 10.1016/j.ijleo.2018.05.013 10.1016/s0262-8856(97)00070-x 10.11591/ijeecs.v18.i2.pp1015-1027 10.3390/s23208559 10.1155/2018/3803627 10.1109/tcsvt.2024.3419933 10.1609/aaai.v35i4.16465 10.1109/CVPR.2013.456 10.1155/2021/5591020 10.1007/s11760-021-02050-w 10.1007/s10462-019-09742-3 10.1007/978-3-031-20233-9_18 10.1016/j.neucom.2022.04.127 10.1007/s11760-019-01436-1 10.1007/s00371-024-03613-x 10.1016/j.patcog.2024.111227 10.1016/j.imavis.2021.104245 10.1109/tifs.2025.3570121 10.32604/csse.2023.027986 10.1007/978-3-319-97909-0_46 10.1007/978-3-030-01264-9_9 10.1142/s0218001422540179 10.1109/cvpr.2019.00482 10.1016/j.eswa.2019.112854 10.1016/j.ins.2021.10.059 10.1016/j.optlastec.2025.113667 10.1016/j.patcog.2023.110049 10.1109/tbiom.2024.3352164 10.1016/j.imavis.2020.104093 10.1109/tpami.2013.50 10.1007/s11042-023-18007-9 10.1109/cvprw50498.2020.00407 10.1109/tpami.2007.250598 10.1016/j.eswa.2024.126150 10.1109/tnnls.2024.3393072 10.1109/CVPR52688.2022.01553 10.3390/app122311885 10.1016/j.neucom.2024.128708 10.3390/app12063144 10.1109/iccvw.2019.00333 10.1016/j.eswa.2024.123302 10.1109/tifs.2018.2833032 10.1007/s10489-020-02100-9 10.1016/j.patcog.2022.108585 10.1016/j.neucom.2016.10.049 10.1016/j.knosys.2025.113922 10.1016/j.compeleceng.2021.107461 10.14569/ijacsa.2022.01309120 10.1109/iccvw54120.2021.00172 10.1038/s41598-024-82965-9 10.1016/j.imavis.2022.104429 10.1109/IPEC51340.2021.9421118 10.1016/j.neucom.2024.128626 10.1109/ICOSP.2014.7015203 10.1109/tpami.2021.3098962
ContentType	Journal Article
Copyright	Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2025
Copyright_xml	– notice: Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2025
DBID	97E ESBDL RIA RIE AAYXX CITATION 7SC 7SP 7SR 8BQ 8FD JG9 JQ2 L7M L~C L~D DOA
DOI	10.1109/ACCESS.2025.3632159
DatabaseName	IEEE Xplore (IEEE) IEEE Xplore Open Access Journals (WRLC) IEEE All-Society Periodicals Package (ASPP) 1998–Present IEEE Xplore CrossRef Computer and Information Systems Abstracts Electronics & Communications Abstracts Engineered Materials Abstracts METADEX Technology Research Database Materials Research Database ProQuest Computer Science Collection Advanced Technologies Database with Aerospace Computer and Information Systems Abstracts Academic Computer and Information Systems Abstracts Professional DOAJ Directory of Open Access Journals
DatabaseTitle	CrossRef Materials Research Database Engineered Materials Abstracts Technology Research Database Computer and Information Systems Abstracts – Academic Electronics & Communications Abstracts ProQuest Computer Science Collection Computer and Information Systems Abstracts Advanced Technologies Database with Aerospace METADEX Computer and Information Systems Abstracts Professional
DatabaseTitleList	Materials Research Database
Database_xml	– sequence: 1 dbid: DOA name: DOAJ Directory of Open Access Journals url: https://www.doaj.org/ sourceTypes: Open Website – sequence: 2 dbid: RIE name: IEEE Electronic Library (IEL) url: https://ieeexplore.ieee.org/ sourceTypes: Publisher
DeliveryMethod	fulltext_linktorsrc
Discipline	Engineering
EISSN	2169-3536
EndPage	195103
ExternalDocumentID	oai_doaj_org_article_886a0b5748c344619b5011623f9db382 10_1109_ACCESS_2025_3632159 11241209
Genre	orig-research
GroupedDBID	0R~ 4.4 5VS 6IK 97E AAJGR ABVLG ACGFS ADBBV AGSQL ALMA_UNASSIGNED_HOLDINGS BCNDV BEFXN BFFAM BGNUA BKEBE BPEOZ EBS EJD ESBDL GROUPED_DOAJ IPLJI JAVBF KQ8 M43 M~E O9- OCL OK1 RIA RIE RNS AAYXX CITATION 7SC 7SP 7SR 8BQ 8FD ABAZT JG9 JQ2 L7M L~C L~D
ID	FETCH-LOGICAL-c2769-1cb7263b2558045d8fe20ee9831eb566f19cd677d3bce7b057e4c7ca809a5f953
IEDL.DBID	RIE
ISSN	2169-3536
IngestDate	Mon Nov 24 19:21:03 EST 2025 Fri Nov 21 23:40:29 EST 2025 Thu Nov 27 00:37:08 EST 2025 Wed Nov 26 07:20:01 EST 2025
IsDoiOpenAccess	true
IsOpenAccess	true
IsPeerReviewed	true
IsScholarly	true
Language	English
License	https://creativecommons.org/licenses/by/4.0/legalcode
LinkModel	DirectLink
MergedId	FETCHMERGED-LOGICAL-c2769-1cb7263b2558045d8fe20ee9831eb566f19cd677d3bce7b057e4c7ca809a5f953
Notes	ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14
ORCID	0009-0009-5629-2560 0000-0001-5781-6754
OpenAccessLink	https://ieeexplore.ieee.org/document/11241209
PQID	3273964936
PQPubID	4845423
PageCount	24
ParticipantIDs	proquest_journals_3273964936 doaj_primary_oai_doaj_org_article_886a0b5748c344619b5011623f9db382 crossref_primary_10_1109_ACCESS_2025_3632159 ieee_primary_11241209
PublicationCentury	2000
PublicationDate	20250000 2025-00-00 20250101 2025-01-01
PublicationDateYYYYMMDD	2025-01-01
PublicationDate_xml	– year: 2025 text: 20250000
PublicationDecade	2020
PublicationPlace	Piscataway
PublicationPlace_xml	– name: Piscataway
PublicationTitle	IEEE access
PublicationTitleAbbrev	Access
PublicationYear	2025
Publisher	IEEE The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Publisher_xml	– name: IEEE – name: The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
References	ref13 ref57 ref12 ref56 ref15 ref59 ref14 ref58 ref53 ref52 ref11 ref55 ref54 ref17 ref16 ref19 ref18 Ullah (ref35) 2020; 16 Chandra (ref25) 2020; 9 ref51 ref50 ref46 ref45 ref48 ref47 ref42 ref41 ref43 ref49 ref7 ref9 ref4 ref3 ref6 ref5 ref40 Albert (ref26) 2020; 98 ref34 ref37 ref31 ref30 ref33 ref32 ref2 ref1 Hassan (ref10) 2021; 5 ref39 ref38 Fahad (ref36) 2020; 28 ref70 ref24 Kingma (ref44) ref23 ref67 ref69 ref20 ref64 ref63 ref22 ref66 ref21 ref65 ref28 ref27 ref29 Goodfellow (ref8) 2016 Mandal (ref68) 2021 ref60 ref62 ref61
References_xml	– ident: ref33 doi: 10.1111/exsy.13625 – volume: 98 start-page: 5067 issue: 22 year: 2020 ident: ref26 article-title: Real and simulated masked face recognition with a pre-trained model publication-title: J. Theor. Appl. Inf. Technol. (JATIT) – ident: ref48 doi: 10.1016/j.imavis.2009.08.002 – ident: ref2 doi: 10.3390/s25051574 – ident: ref58 doi: 10.1109/iccvw.2019.00322 – ident: ref12 doi: 10.3390/s20020342 – ident: ref64 doi: 10.3390/electronics14091736 – ident: ref9 doi: 10.1016/j.patcog.2023.110127 – ident: ref17 doi: 10.1016/j.ijleo.2018.05.013 – ident: ref45 doi: 10.1016/s0262-8856(97)00070-x – ident: ref24 doi: 10.11591/ijeecs.v18.i2.pp1015-1027 – ident: ref6 doi: 10.3390/s23208559 – ident: ref67 doi: 10.1155/2018/3803627 – start-page: 1 volume-title: Proc. Int. Conf. Learn. Represent. (ICLR) ident: ref44 article-title: Adam: A method for stochastic optimization – ident: ref1 doi: 10.1109/tcsvt.2024.3419933 – ident: ref54 doi: 10.1609/aaai.v35i4.16465 – ident: ref13 doi: 10.1109/CVPR.2013.456 – volume: 9 start-page: 5185 issue: 10 year: 2020 ident: ref25 article-title: A comparative analysis of face recognition models on masked faces publication-title: Int. J. Sci. Technol. Res. (IJSTR) – ident: ref69 doi: 10.1155/2021/5591020 – volume: 28 start-page: 543 issue: 3 year: 2020 ident: ref36 article-title: Optimizing dual energy X-ray image enhancement using a novel hybrid fusion method publication-title: J. X-Ray Sci. Technol. – ident: ref28 doi: 10.1007/s11760-021-02050-w – ident: ref46 doi: 10.1007/s10462-019-09742-3 – ident: ref50 doi: 10.1007/978-3-031-20233-9_18 – ident: ref41 doi: 10.1016/j.neucom.2022.04.127 – ident: ref51 doi: 10.1007/s11760-019-01436-1 – ident: ref20 doi: 10.1007/s00371-024-03613-x – ident: ref3 doi: 10.1016/j.patcog.2024.111227 – ident: ref38 doi: 10.1016/j.imavis.2021.104245 – ident: ref32 doi: 10.1109/tifs.2025.3570121 – year: 2021 ident: ref68 article-title: Masked face recognition using ResNet-50 publication-title: arXiv:2104.08997 – ident: ref29 doi: 10.32604/csse.2023.027986 – volume: 16 start-page: 1005 issue: 5 year: 2020 ident: ref35 article-title: A novel approach to enhance dual-energy X-ray images using region of interest and discrete wavelet transform publication-title: J. Inf. Process. Syst. (JIPS) – ident: ref53 doi: 10.1007/978-3-319-97909-0_46 – ident: ref42 doi: 10.1007/978-3-030-01264-9_9 – ident: ref47 doi: 10.1142/s0218001422540179 – ident: ref18 doi: 10.1109/cvpr.2019.00482 – ident: ref66 doi: 10.1016/j.eswa.2019.112854 – ident: ref63 doi: 10.1016/j.ins.2021.10.059 – ident: ref34 doi: 10.1016/j.optlastec.2025.113667 – ident: ref7 doi: 10.1016/j.patcog.2023.110049 – ident: ref59 doi: 10.1109/tbiom.2024.3352164 – ident: ref65 doi: 10.1016/j.imavis.2020.104093 – ident: ref39 doi: 10.1109/tpami.2013.50 – ident: ref49 doi: 10.1007/s11042-023-18007-9 – ident: ref11 doi: 10.1109/cvprw50498.2020.00407 – ident: ref43 doi: 10.1109/tpami.2007.250598 – ident: ref21 doi: 10.1016/j.eswa.2024.126150 – ident: ref31 doi: 10.1109/tnnls.2024.3393072 – ident: ref19 doi: 10.1109/CVPR52688.2022.01553 – ident: ref62 doi: 10.3390/app122311885 – volume-title: Deep Learning year: 2016 ident: ref8 – ident: ref5 doi: 10.1016/j.neucom.2024.128708 – ident: ref16 doi: 10.3390/app12063144 – ident: ref57 doi: 10.1109/iccvw.2019.00333 – ident: ref4 doi: 10.1016/j.eswa.2024.123302 – ident: ref55 doi: 10.1109/tifs.2018.2833032 – ident: ref70 doi: 10.1007/s10489-020-02100-9 – ident: ref60 doi: 10.1016/j.patcog.2022.108585 – ident: ref40 doi: 10.1016/j.neucom.2016.10.049 – volume: 5 start-page: 81 issue: 1 year: 2021 ident: ref10 article-title: Deep learning convolutional neural network for face recognition: A review publication-title: Int. J. Sci. Bus. – ident: ref23 doi: 10.1016/j.knosys.2025.113922 – ident: ref15 doi: 10.1016/j.compeleceng.2021.107461 – ident: ref27 doi: 10.14569/ijacsa.2022.01309120 – ident: ref52 doi: 10.1109/iccvw54120.2021.00172 – ident: ref22 doi: 10.1038/s41598-024-82965-9 – ident: ref56 doi: 10.1016/j.imavis.2022.104429 – ident: ref61 doi: 10.1109/IPEC51340.2021.9421118 – ident: ref30 doi: 10.1016/j.neucom.2024.128626 – ident: ref14 doi: 10.1109/ICOSP.2014.7015203 – ident: ref37 doi: 10.1109/tpami.2021.3098962
SSID	ssj0000816957
Score	2.3347487
Snippet	This paper presents a novel approach for improving occluded face recognition performance using a family of autoencoders (AE) architectures. The proposed...
SourceID	doaj proquest crossref ieee
SourceType	Open Website Aggregation Database Index Database Publisher
StartPage	195080
SubjectTerms	Accuracy Artificial neural networks Autoencoders Coders Convolutional autoencoder Convolutional codes Convolutional neural networks Datasets Deep learning Deepfakes Face recognition Feature extraction Image reconstruction occluded dataset Occlusion Performance evaluation Robustness self-supervised autoencoder smooth autoencoder Transformers
SummonAdditionalLinks	– databaseName: DOAJ Directory of Open Access Journals dbid: DOA link: http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrV25TsQwELUQooACcYrlkgtKAomd2B66ZWEFDVCARGfFRwQSZNEmy_czdgIsoqChjJXI8Ztk5o2PN4Qc-VwYbqxJXFWxJGdllZSe-QRDcWFBQVgcjMUm5M2NenyEu7lSX2FPWCcP3AF3qpQoU1PIXFmOqUsGpghrB4xX4AxX0fsi65lLpqIPVpmAQvYyQ1kKp8PRCEeECSErTrjgGOngRyiKiv19iZVffjkGm_EaWe1ZIh12b7dOFny9QVbmtAM3STmctZPksg5n0qcNvcDm9yji3dBJTS_6uictvbX2Zea8o-PSenr9iv6jOaPBDUz9U7d7nXYLBLSsHUWnh5fN7KVttsjD-PJ-dJX09RISy6SAJLNGMsENZgkKmZpTlWep96B45g3StioD64SUDo3jpUGm5nMrbalSKIsKCr5NFutJ7XcIRd7nEG8mWQU52hMKazw-xSCzUuRiQI4_odNvnSyGjulECrpDWgekdY_0gJwHeL9uDZrWsQEtrXtL678sPSBbwTjf_SE1CSd_B2T_01q6_wEbzZGWgciBi93_6HuPLIfxdHMv-2Sxnc78AVmy7-1zMz2M394HGxfYeg priority: 102 providerName: Directory of Open Access Journals
Title	Auto-Encoders Derivatives on Different Occluded Face Images: Comprehensive Review and New Results
URI	https://ieeexplore.ieee.org/document/11241209 https://www.proquest.com/docview/3273964936 https://doaj.org/article/886a0b5748c344619b5011623f9db382
Volume	13
hasFullText	1
inHoldings	1
isFullTextHit
isPrint
journalDatabaseRights	– providerCode: PRVAON databaseName: DOAJ Directory of Open Access Journals customDbUrl: eissn: 2169-3536 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0000816957 issn: 2169-3536 databaseCode: DOA dateStart: 20130101 isFulltext: true titleUrlDefault: https://www.doaj.org/ providerName: Directory of Open Access Journals – providerCode: PRVHPJ databaseName: ROAD: Directory of Open Access Scholarly Resources customDbUrl: eissn: 2169-3536 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0000816957 issn: 2169-3536 databaseCode: M~E dateStart: 20130101 isFulltext: true titleUrlDefault: https://road.issn.org providerName: ISSN International Centre
link	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1Lb9QwELZoxQEOPItYKJUPHEmb2I7t4bZsdwUHCgeQeotieyKQShZtkh772zt23AJCHLhEiRXLjr94np4Zxl6j0k4674rQdaJQou2KFgUWxIprDxaiczAVmzBnZ_b8HD7nYPUUC4OI6fAZHsfb5MsPWz9FU9kJyQYqxnrusT1jzBysdWtQiRUkoDY5s1BVwslytaKPIB1Q1MdSS2Ju8Af3SUn6c1WVv0hx4i-bh_85s0fsQRYk-XJG_jG7g_0Tdv-39IJPWbucxm2x7mPY-m7gp9R8mfJ8D3zb89NcGmXkn7y_mAIGvmk98g8_iMQMb3mkFDv8Nh9w57MPgbd94EQX6XGYLsbhgH3drL-s3he5pELhhdFQVN4ZoaUjRcKSMBdsh6JEBCsrdCTZdRX4oI0JhB8aR8IcKm98a0to6w5q-Yzt99senzNOomHwUgkjOlAEOdTeIfUSUHmjlV6wNzdL3fycM2c0SeMooZmRaSIyTUZmwd5FOG5fjWmvUwOtc5N3UWOtbktXG2VpZEW6n6ujI0nIDoKTVizYQcTm13gZlgU7vEG3yXt0aCRJbqAVSP3iH91esntxirPF5ZDtj7sJX7G7_nL8PuyOkvpO149X66P0K14DHHfZ7g
linkProvider	IEEE
linkToHtml	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1Lb9QwELagIAEHnq1YKOADR9ImtuMHt2XbVSvKwqFIvVmxPRFIbRZtkv5-xo5bQKiH3pIolh1_8cw3Hs8MIe9BSMedd0VoW1YI1rRFAwwKVMW1N9pE52AqNqFWK312Zr7lYPUUCwMA6fAZ7MXL5MsPaz_GrbJ95AYixnreJfdqIVg1hWtdb6nEGhKmVjm3UFWa_fligZ-BViCr97jkqN7MP_onpenPdVX-E8ZJwyyf3HJsT8njTCXpfML-GbkD3XPy6K8Egy9IMx-HdXHYxcD1TU8P8PFlyvTd03VHD3JxlIF-9f58DBDosvFAjy9QyPQfaZQVG_gxHXGnkxeBNl2gKBnxth_Ph36bfF8eni6OilxUofBMSVNU3ikmuUNTQiOdC7oFVgIYzStwyO3ayvgglQqIICiHdA6EV77RpWnq1tR8h2x16w5eEorkMHgumGKtEQi6qb0DbMVM5ZUUckY-XE21_TXlzrDJ5iiNnZCxERmbkZmRTxGO61dj4uv0AOfZ5nVktZZN6WolNPYs0PpzdXQlMd6a4LhmM7IdsfnTX4ZlRnav0LV5lfaWI3czUhguX93Q7B15cHT65cSeHK8-vyYP43Cn_ZddsjVsRnhD7vvL4We_eZt-xd9ULtsP
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%3Ajournal&rft.genre=article&rft.atitle=Auto-Encoders+Derivatives+on+Different+Occluded+Face+Images%3A+Comprehensive+Review+and+New+Results&rft.jtitle=IEEE+access&rft.au=Masoudi%2C+Azin&rft.au=Ahmadi%2C+Majid&rft.date=2025&rft.pub=IEEE&rft.eissn=2169-3536&rft.volume=13&rft.spage=195080&rft.epage=195103&rft_id=info:doi/10.1109%2FACCESS.2025.3632159&rft.externalDocID=11241209
thumbnail_l	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=2169-3536&client=summon
thumbnail_m	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=2169-3536&client=summon
thumbnail_s	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=2169-3536&client=summon