Deep D2C-Net: deep learning-based display-to-camera communications
In this paper, we propose Deep D2C-Net, a novel display-to-camera (D2C) communications technique using deep convolutional neural networks (DCNNs) for data embedding and extraction with images. The proposed technique consists of fully end-to-end encoding and decoding networks, which respectively prod...
Saved in:
Published in | Optics express Vol. 29; no. 8; pp. 11494 - 11511 |
---|---|
Main Authors | , |
Format | Journal Article |
Language | English |
Published |
United States
12.04.2021
|
Online Access | Get full text |
Cover
Loading…
Abstract | In this paper, we propose Deep D2C-Net, a novel display-to-camera (D2C) communications technique using deep convolutional neural networks (DCNNs) for data embedding and extraction with images. The proposed technique consists of fully end-to-end encoding and decoding networks, which respectively produce high-quality data-embedded images and enable robust data acquisition in the presence of optical wireless channel. For encoding, Hybrid layers are introduced where the concurrent feature maps of the intended data and cover images are concatenated in a feed-forward fashion; for decoding, a simple convolutional neural network (CNN) is utilized. We conducted experiments in a real-world environment using a smartphone camera and a digital display with multiple parameters, such as transmission distance, capture angle, display brightness, and resolution of the camera. Experimental results prove that Deep D2C-Net outperforms the existing state-of-the-art algorithms in terms of peak signal-to-noise ratio (PSNR) and bit error rate (BER), while the data-embedded image displayed on the screen yields high visual quality for the human eye. |
---|---|
AbstractList | In this paper, we propose Deep D2C-Net, a novel display-to-camera (D2C) communications technique using deep convolutional neural networks (DCNNs) for data embedding and extraction with images. The proposed technique consists of fully end-to-end encoding and decoding networks, which respectively produce high-quality data-embedded images and enable robust data acquisition in the presence of optical wireless channel. For encoding, Hybrid layers are introduced where the concurrent feature maps of the intended data and cover images are concatenated in a feed-forward fashion; for decoding, a simple convolutional neural network (CNN) is utilized. We conducted experiments in a real-world environment using a smartphone camera and a digital display with multiple parameters, such as transmission distance, capture angle, display brightness, and resolution of the camera. Experimental results prove that Deep D2C-Net outperforms the existing state-of-the-art algorithms in terms of peak signal-to-noise ratio (PSNR) and bit error rate (BER), while the data-embedded image displayed on the screen yields high visual quality for the human eye. |
Author | Kim, Byung Wook Tamang, Lakpa Dorje |
Author_xml | – sequence: 1 givenname: Lakpa Dorje surname: Tamang fullname: Tamang, Lakpa Dorje – sequence: 2 givenname: Byung Wook surname: Kim fullname: Kim, Byung Wook |
BackLink | https://www.ncbi.nlm.nih.gov/pubmed/33984927$$D View this record in MEDLINE/PubMed |
BookMark | eNpNkMtOwzAQRS1URGlhwQ-gLGHhMn7FCTtoy0Oq6AbWlhM7KCixg50s-vekakGs5s7o6Gp0ZmjivLMIXRFYEJbyu-16wSkVOTlB5wRyjjlkcvIvT9Esxi8AwmUuz9CUsTzjOZXn6HFlbZes6BK_2f4-MfutsTq42n3iQkdrElPHrtE73Htc6tYGnZS-bQdXl7qvvYsX6LTSTbSXxzlHH0_r9-UL3myfX5cPG1wyCj3mvLBGpkwLIhgALYBUjPFMCmN4lunx_zELPV5NWQgpUiYAUi2hqCAVwObo5tDbBf892Nirto6lbRrtrB-iooJmRI4-xIjeHtAy-BiDrVQX6laHnSKg9srUdq0Oykb2-lg7FK01f-SvI_YDeIZlBQ |
CitedBy_id | crossref_primary_10_1109_ACCESS_2023_3331754 crossref_primary_10_1364_OE_522020 crossref_primary_10_3390_app12157538 crossref_primary_10_3390_app13179916 crossref_primary_10_3390_app112210982 crossref_primary_10_1364_OE_498067 crossref_primary_10_1364_OE_528013 |
Cites_doi | 10.1109/TPAMI.2017.2699184 10.1364/JOCN.9.000D51 10.7840/kics.2017.42.1.8 10.1109/MCE.2016.2640698 10.1109/COMST.2018.2838096 10.1109/COMST.2020.2966855 10.1109/JPHOT.2015.2486680 10.1145/2896818 10.1109/ACCESS.2017.2681110 10.1109/JLT.2015.2499186 10.1364/OE.409395 10.1145/2721896.2721910 10.1109/MSP.2018.2842646 10.1109/JSTARS.2014.2329330 10.3837/tiis.2020.03.017 10.1109/ACCESS.2020.2971984 10.1109/JPHOT.2019.2948071 10.1109/ACCESS.2020.2990528 |
ContentType | Journal Article |
DBID | NPM AAYXX CITATION 7X8 |
DOI | 10.1364/OE.422591 |
DatabaseName | PubMed CrossRef MEDLINE - Academic |
DatabaseTitle | PubMed CrossRef MEDLINE - Academic |
DatabaseTitleList | PubMed CrossRef |
Database_xml | – sequence: 1 dbid: NPM name: PubMed url: https://proxy.k.utb.cz/login?url=http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed sourceTypes: Index Database |
DeliveryMethod | fulltext_linktorsrc |
Discipline | Physics |
EISSN | 1094-4087 |
EndPage | 11511 |
ExternalDocumentID | 10_1364_OE_422591 33984927 |
Genre | Journal Article |
GroupedDBID | --- 123 29N 2WC 8SL AAWJZ ACGFO ADBBV AENEX AKGWG ALMA_UNASSIGNED_HOLDINGS ATHME AYPRP AZSQR AZYMN BAWUL BCNDV CS3 DIK DSZJF DU5 E3Z EBS F5P GROUPED_DOAJ GX1 KQ8 M~E NPM OFLFD OK1 OPJBK OPLUZ P2P RNS ROL ROP ROS TR2 TR6 XSB AAYXX CITATION 7X8 |
ID | FETCH-LOGICAL-c320t-44bed763a5153002b01f334875dd488a2598755a1f3dcb575635006a70bf06503 |
ISSN | 1094-4087 |
IngestDate | Fri Jun 28 01:45:08 EDT 2024 Wed Aug 07 14:00:09 EDT 2024 Thu May 23 23:42:13 EDT 2024 |
IsDoiOpenAccess | false |
IsOpenAccess | true |
IsPeerReviewed | true |
IsScholarly | true |
Issue | 8 |
Language | English |
LinkModel | OpenURL |
MergedId | FETCHMERGED-LOGICAL-c320t-44bed763a5153002b01f334875dd488a2598755a1f3dcb575635006a70bf06503 |
Notes | ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 23 |
ORCID | 0000-0002-4728-9011 0000-0003-3915-8166 |
OpenAccessLink | https://doi.org/10.1364/oe.422591 |
PMID | 33984927 |
PQID | 2528173645 |
PQPubID | 23479 |
PageCount | 18 |
ParticipantIDs | proquest_miscellaneous_2528173645 crossref_primary_10_1364_OE_422591 pubmed_primary_33984927 |
PublicationCentury | 2000 |
PublicationDate | 2021-Apr-12 2021-04-12 20210412 |
PublicationDateYYYYMMDD | 2021-04-12 |
PublicationDate_xml | – month: 04 year: 2021 text: 2021-Apr-12 day: 12 |
PublicationDecade | 2020 |
PublicationPlace | United States |
PublicationPlace_xml | – name: United States |
PublicationTitle | Optics express |
PublicationTitleAlternate | Opt Express |
PublicationYear | 2021 |
References | Chen (oe-29-8-11494-R18) 2014; 7 Chen (oe-29-8-11494-R19) 2018; 40 Lain (oe-29-8-11494-R3) 2019; 11 Luo (oe-29-8-11494-R2) 2015; 7 Rahaim (oe-29-8-11494-R5) 2017; 9 Jo (oe-29-8-11494-R11) 2016; 35 Wang (oe-29-8-11494-R6) 2021; 29 Neupane (oe-29-8-11494-R20) 2020; 8 Nguyen (oe-29-8-11494-R31) 2017; 5 Lemley (oe-29-8-11494-R17) 2017; 6 Alajmi (oe-29-8-11494-R7) 2020; 8 Chowdhury (oe-29-8-11494-R32) 2020; 22 Gonzalez (oe-29-8-11494-R16) 2018; 35 Al-Kinani (oe-29-8-11494-R4) 2018; 20 Li (oe-29-8-11494-R12) 2015; 18 Kim (oe-29-8-11494-R13) 2015; 33 Hussain (oe-29-8-11494-R21) 2020; 14 Le (oe-29-8-11494-R1) 2017; 42 |
References_xml | – volume: 40 start-page: 834 year: 2018 ident: oe-29-8-11494-R19 publication-title: IEEE Trans. Pattern Anal. Mach. Intell. doi: 10.1109/TPAMI.2017.2699184 contributor: fullname: Chen – volume: 9 start-page: D51 year: 2017 ident: oe-29-8-11494-R5 publication-title: J. Opt. Commun. Netw. doi: 10.1364/JOCN.9.000D51 contributor: fullname: Rahaim – volume: 42 start-page: 8 year: 2017 ident: oe-29-8-11494-R1 publication-title: J. KICS. doi: 10.7840/kics.2017.42.1.8 contributor: fullname: Le – volume: 6 start-page: 48 year: 2017 ident: oe-29-8-11494-R17 publication-title: IEEE Consumer Electron. Mag. doi: 10.1109/MCE.2016.2640698 contributor: fullname: Lemley – volume: 20 start-page: 1939 year: 2018 ident: oe-29-8-11494-R4 publication-title: IEEE Commun. Surv. Tutorials doi: 10.1109/COMST.2018.2838096 contributor: fullname: Al-Kinani – volume: 22 start-page: 930 year: 2020 ident: oe-29-8-11494-R32 publication-title: IEEE Commun. Surv. Tutorials doi: 10.1109/COMST.2020.2966855 contributor: fullname: Chowdhury – volume: 7 start-page: 1 year: 2015 ident: oe-29-8-11494-R2 publication-title: IEEE Photonics J. doi: 10.1109/JPHOT.2015.2486680 contributor: fullname: Luo – volume: 35 start-page: 1 year: 2016 ident: oe-29-8-11494-R11 publication-title: ACM Trans. Graph. doi: 10.1145/2896818 contributor: fullname: Jo – volume: 5 start-page: 4574 year: 2017 ident: oe-29-8-11494-R31 publication-title: IEEE Access doi: 10.1109/ACCESS.2017.2681110 contributor: fullname: Nguyen – volume: 33 start-page: 5269 year: 2015 ident: oe-29-8-11494-R13 publication-title: J. Lightwave Technol. doi: 10.1109/JLT.2015.2499186 contributor: fullname: Kim – volume: 29 start-page: 4582 year: 2021 ident: oe-29-8-11494-R6 publication-title: Opt. Express doi: 10.1364/OE.409395 contributor: fullname: Wang – volume: 18 start-page: 62 year: 2015 ident: oe-29-8-11494-R12 publication-title: SIGMOBILE Mob. Comput. Commun. Rev. doi: 10.1145/2721896.2721910 contributor: fullname: Li – volume: 35 start-page: 79 year: 2018 ident: oe-29-8-11494-R16 publication-title: IEEE Signal Process. Mag. doi: 10.1109/MSP.2018.2842646 contributor: fullname: Gonzalez – volume: 7 start-page: 2094 year: 2014 ident: oe-29-8-11494-R18 publication-title: IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing doi: 10.1109/JSTARS.2014.2329330 contributor: fullname: Chen – volume: 14 start-page: 1228 year: 2020 ident: oe-29-8-11494-R21 publication-title: KSII Trans. on Int. and Info. Sys. doi: 10.3837/tiis.2020.03.017 contributor: fullname: Hussain – volume: 8 start-page: 27861 year: 2020 ident: oe-29-8-11494-R7 publication-title: IEEE Access doi: 10.1109/ACCESS.2020.2971984 contributor: fullname: Alajmi – volume: 11 start-page: 1 year: 2019 ident: oe-29-8-11494-R3 publication-title: IEEE Photonics J. doi: 10.1109/JPHOT.2019.2948071 contributor: fullname: Lain – volume: 8 start-page: 93155 year: 2020 ident: oe-29-8-11494-R20 publication-title: IEEE Access doi: 10.1109/ACCESS.2020.2990528 contributor: fullname: Neupane |
SSID | ssj0014797 |
Score | 2.4348342 |
Snippet | In this paper, we propose Deep D2C-Net, a novel display-to-camera (D2C) communications technique using deep convolutional neural networks (DCNNs) for data... |
SourceID | proquest crossref pubmed |
SourceType | Aggregation Database Index Database |
StartPage | 11494 |
Title | Deep D2C-Net: deep learning-based display-to-camera communications |
URI | https://www.ncbi.nlm.nih.gov/pubmed/33984927 https://search.proquest.com/docview/2528173645 |
Volume | 29 |
hasFullText | 1 |
inHoldings | 1 |
isFullTextHit | |
isPrint | |
link | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV1da9swFBVdR2EvYx_dln0Ub_StqEtk2bL3trYuZaTJS0LzZiRLKbRbYhoX1j3st-_oI05DN-j6YhxBBLlHOffcK11dQnZFXkkjOKeJ0dyW5AiqMlXRFNocDler1Nh659NBejLm3ybJZNUz01WXNGq_-vXXupKHoIox4GqrZP8D2XZSDOAd-OIJhPG8F8ZHxtR7R-yQDozL8Gn7OfSBOKfWQWm7A1N_lze0mdNK2gyUPUW-qglZ3Fanw9pd2mx-1u3BDBfU_whJ5b68rCU099VFuxxCN-aDG5DG3tlSsYc0AutRd1-h9wKe-hDoIZoM7i9wY8hG-DWQ3SI6hFG-OXHwmhCWnjTvUHKccthxWOxzUIfvzLV-7fVgWB6P-_1yVExGj8hjJvLERtGnv4t2O4iLXIRroTDd53aydTHxjwjBKYXRM_I0SPzoq8frOdkwsxdkyx21rRYvyYFFLQqofYksZtE6ZtEdzKJ1zLbJ-LgYHZ7Q0MmCVjHrNpRzZTSYXEI9xvBBqtub2hJokWgNBpX4LXhPJEZ1paCgIQNBh1J01dRq6PgV2ZzNZ-YNiVIj2ZTrbp7lkqskw58JlM24zKzUNqZDPi1NUtb-wpLS7VqmvBwWpbdbh3xcGqsEndg9Ijkz8-tFyRKW9YTdm-6Q196K7TRxnGc8Z-LtPb79jjxZrbL3ZLO5ujYfIN8atePSHjsO4D_3JUVT |
link.rule.ids | 315,786,790,870,27957,27958 |
linkProvider | ISSN International Centre |
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=Deep+D2C-Net%3A+deep+learning-based+display-to-camera+communications&rft.jtitle=Optics+express&rft.au=Tamang%2C+Lakpa+Dorje&rft.au=Kim%2C+Byung+Wook&rft.date=2021-04-12&rft.eissn=1094-4087&rft.volume=29&rft.issue=8&rft.spage=11494&rft.epage=11511&rft_id=info:doi/10.1364%2FOE.422591&rft.externalDBID=NO_FULL_TEXT |
thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1094-4087&client=summon |
thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1094-4087&client=summon |
thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1094-4087&client=summon |