Deringing and denoising in extremely under-sampled Fourier single pixel imaging
Undersampling in Fourier single pixel imaging (FSI) is often employed to reduce imaging time for real-time applications. However, the undersampled reconstruction contains ringing artifacts (Gibbs phenomenon) that occur because the high-frequency target information is not recorded. Furthermore, by em...
Uloženo v:
| Vydáno v: | Optics express Ročník 28; číslo 5; s. 7360 |
|---|---|
| Hlavní autoři: | , , , |
| Médium: | Journal Article |
| Jazyk: | angličtina |
| Vydáno: |
United States
02.03.2020
|
| ISSN: | 1094-4087, 1094-4087 |
| On-line přístup: | Získat plný text |
| Tagy: |
Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
|
| Abstract | Undersampling in Fourier single pixel imaging (FSI) is often employed to reduce imaging time for real-time applications. However, the undersampled reconstruction contains ringing artifacts (Gibbs phenomenon) that occur because the high-frequency target information is not recorded. Furthermore, by employing 3-step FSI strategy (reduced measurements with low noise suppression) with a low-grade sensor (i.e., photodiode), this ringing is coupled with noise to produce unwanted artifacts, lowering image quality. To improve the imaging quality of real-time FSI, a fast image reconstruction framework based on deep convolutional autoencoder network (DCAN) is proposed. The network through context learning over FSI artifacts is capable of deringing, denoising, and recovering details in 256 × 256 images. The promising experimental results show that the proposed deep-learning-based FSI outperforms conventional FSI in terms of image quality even at very low sampling rates (1-4%). |
|---|---|
| AbstractList | Undersampling in Fourier single pixel imaging (FSI) is often employed to reduce imaging time for real-time applications. However, the undersampled reconstruction contains ringing artifacts (Gibbs phenomenon) that occur because the high-frequency target information is not recorded. Furthermore, by employing 3-step FSI strategy (reduced measurements with low noise suppression) with a low-grade sensor (i.e., photodiode), this ringing is coupled with noise to produce unwanted artifacts, lowering image quality. To improve the imaging quality of real-time FSI, a fast image reconstruction framework based on deep convolutional autoencoder network (DCAN) is proposed. The network through context learning over FSI artifacts is capable of deringing, denoising, and recovering details in 256 × 256 images. The promising experimental results show that the proposed deep-learning-based FSI outperforms conventional FSI in terms of image quality even at very low sampling rates (1-4%). Undersampling in Fourier single pixel imaging (FSI) is often employed to reduce imaging time for real-time applications. However, the undersampled reconstruction contains ringing artifacts (Gibbs phenomenon) that occur because the high-frequency target information is not recorded. Furthermore, by employing 3-step FSI strategy (reduced measurements with low noise suppression) with a low-grade sensor (i.e., photodiode), this ringing is coupled with noise to produce unwanted artifacts, lowering image quality. To improve the imaging quality of real-time FSI, a fast image reconstruction framework based on deep convolutional autoencoder network (DCAN) is proposed. The network through context learning over FSI artifacts is capable of deringing, denoising, and recovering details in 256 × 256 images. The promising experimental results show that the proposed deep-learning-based FSI outperforms conventional FSI in terms of image quality even at very low sampling rates (1-4%).Undersampling in Fourier single pixel imaging (FSI) is often employed to reduce imaging time for real-time applications. However, the undersampled reconstruction contains ringing artifacts (Gibbs phenomenon) that occur because the high-frequency target information is not recorded. Furthermore, by employing 3-step FSI strategy (reduced measurements with low noise suppression) with a low-grade sensor (i.e., photodiode), this ringing is coupled with noise to produce unwanted artifacts, lowering image quality. To improve the imaging quality of real-time FSI, a fast image reconstruction framework based on deep convolutional autoencoder network (DCAN) is proposed. The network through context learning over FSI artifacts is capable of deringing, denoising, and recovering details in 256 × 256 images. The promising experimental results show that the proposed deep-learning-based FSI outperforms conventional FSI in terms of image quality even at very low sampling rates (1-4%). |
| Author | Cao, Jie Zhang, Kaiyu Hao, Qun Rizvi, Saad |
| Author_xml | – sequence: 1 givenname: Saad orcidid: 0000-0003-3942-0857 surname: Rizvi fullname: Rizvi, Saad – sequence: 2 givenname: Jie surname: Cao fullname: Cao, Jie – sequence: 3 givenname: Kaiyu surname: Zhang fullname: Zhang, Kaiyu – sequence: 4 givenname: Qun surname: Hao fullname: Hao, Qun |
| BackLink | https://www.ncbi.nlm.nih.gov/pubmed/32225966$$D View this record in MEDLINE/PubMed |
| BookMark | eNpt0F1LwzAUBuAgEzenF_4ByaVedEvz0Y9LmZsKg97odUmTM4mkaU1a2P69LZsiIoSTc-DJIbyXaOIaBwjdxGQRs4Qvi_WCZYIydoZmMcl5xEmWTn71U3QZwgchMU_z9AJNGaVU5EkyQ8UjeOPeh4Ol01iDa0wYJ-Mw7DsPNdgD7p0GHwVZtxY03jS9N-Dx6Czg1uzBYlPLccsVOt9JG-D6dM_R22b9unqOtsXTy-phGylGSReJXClBQVSCK6kyAkpSJnRWEZFALBJdSaGrdKip1HHGpM45EJVorkTCSMrm6O64t_XNZw-hK2sTFFgrHTR9KCnLeMZplpKB3p5oX9Wgy9YPf_WH8juEAdwfgfJNCB52PyQm5RhwWazLY8CDXf6xynSyM43rvDT2nxdfNAh8tA |
| CitedBy_id | crossref_primary_10_1038_s41598_020_68401_8 crossref_primary_10_1016_j_optcom_2023_129470 crossref_primary_10_1117_1_JEI_33_2_023044 crossref_primary_10_1002_jbio_202200045 crossref_primary_10_1016_j_optlastec_2023_109710 crossref_primary_10_1016_j_optlaseng_2022_107391 crossref_primary_10_3390_s24102963 crossref_primary_10_1016_j_optlastec_2023_109651 crossref_primary_10_1016_j_optlastec_2025_113655 crossref_primary_10_1109_JSTQE_2023_3272642 crossref_primary_10_1016_j_optlastec_2023_110085 crossref_primary_10_3390_electronics14173463 crossref_primary_10_1109_TTHZ_2021_3132160 crossref_primary_10_3390_app14166875 crossref_primary_10_1007_s11432_022_3553_1 crossref_primary_10_1016_j_optcom_2024_131027 crossref_primary_10_1016_j_optcom_2023_130011 crossref_primary_10_1016_j_optcom_2024_130930 crossref_primary_10_1016_j_optlastec_2024_111249 crossref_primary_10_1109_TCI_2023_3282041 crossref_primary_10_1016_j_optlaseng_2022_106970 crossref_primary_10_1016_j_optlastec_2025_112450 crossref_primary_10_3390_s20247093 crossref_primary_10_1016_j_optlastec_2025_112695 crossref_primary_10_1103_PhysRevApplied_19_044025 crossref_primary_10_1016_j_optlaseng_2022_107406 crossref_primary_10_3390_photonics12060568 crossref_primary_10_1016_j_pes_2025_100056 crossref_primary_10_1364_AO_487479 |
| Cites_doi | 10.1109/TIP.2007.891788 10.1364/OE.25.019619 10.1364/OE.27.025560 10.1364/OL.44.003278 10.1364/OE.26.020009 10.1364/OE.17.008567 10.1038/s41598-018-30390-0 10.1109/TIT.2006.871582 10.1109/TIP.2016.2598681 10.1103/PhysRevA.78.061802 10.1364/AO.58.008471 10.1364/OPTICA.6.000921 10.1364/OE.21.023068 10.1364/OE.25.017466 10.1038/s41598-017-12228-3 10.3390/s19194190 10.1364/OE.26.031094 10.1364/OE.27.014231 10.1364/OE.20.016892 10.1002/mrm.25866 10.1364/JOSAA.29.001556 10.1063/1.3238296 10.1038/s41598-018-20521-y 10.1126/science.1234454 10.1038/ncomms7225 10.1038/s41598-018-24731-2 10.1364/OE.18.007138 10.1038/059200b0 10.1109/TIP.2003.819861 10.1364/OE.26.016547 10.1103/PhysRevLett.104.253603 |
| ContentType | Journal Article |
| DBID | AAYXX CITATION NPM 7X8 |
| DOI | 10.1364/OE.385233 |
| DatabaseName | CrossRef PubMed MEDLINE - Academic |
| DatabaseTitle | CrossRef PubMed MEDLINE - Academic |
| DatabaseTitleList | PubMed MEDLINE - Academic CrossRef |
| Database_xml | – sequence: 1 dbid: NPM name: PubMed url: http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed sourceTypes: Index Database – sequence: 2 dbid: 7X8 name: MEDLINE - Academic url: https://search.proquest.com/medline sourceTypes: Aggregation Database |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Physics |
| EISSN | 1094-4087 |
| ExternalDocumentID | 32225966 10_1364_OE_385233 |
| Genre | Journal Article |
| GroupedDBID | --- 123 29N 2WC 8SL AAFWJ AAWJZ AAYXX ABGOQ ACGFO ADBBV AEDJG AENEX AFPKN AKGWG ALMA_UNASSIGNED_HOLDINGS ATHME AYPRP AZSQR AZYMN BAWUL BCNDV CITATION CS3 DIK DSZJF DU5 E3Z EBS F5P GROUPED_DOAJ GX1 KQ8 M~E OFLFD OK1 OPJBK OPLUZ OVT P2P RNS ROL ROS TR2 TR6 XSB NPM ROP 7X8 |
| ID | FETCH-LOGICAL-c320t-59cc52e5b54cac80eca235d8b056e156dba5db7ba57ad183ad94e0c6d4c563073 |
| ISICitedReferencesCount | 52 |
| ISICitedReferencesURI | http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000518435600117&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| ISSN | 1094-4087 |
| IngestDate | Thu Oct 02 12:09:35 EDT 2025 Wed Feb 19 02:31:11 EST 2025 Sat Nov 29 06:13:41 EST 2025 Tue Nov 18 22:17:48 EST 2025 |
| IsDoiOpenAccess | false |
| IsOpenAccess | true |
| IsPeerReviewed | true |
| IsScholarly | true |
| Issue | 5 |
| Language | English |
| LinkModel | OpenURL |
| MergedId | FETCHMERGED-LOGICAL-c320t-59cc52e5b54cac80eca235d8b056e156dba5db7ba57ad183ad94e0c6d4c563073 |
| Notes | ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 23 |
| ORCID | 0000-0003-3942-0857 |
| OpenAccessLink | https://doi.org/10.1364/oe.385233 |
| PMID | 32225966 |
| PQID | 2384842870 |
| PQPubID | 23479 |
| ParticipantIDs | proquest_miscellaneous_2384842870 pubmed_primary_32225966 crossref_primary_10_1364_OE_385233 crossref_citationtrail_10_1364_OE_385233 |
| PublicationCentury | 2000 |
| PublicationDate | 2020-03-02 2020-Mar-02 20200302 |
| PublicationDateYYYYMMDD | 2020-03-02 |
| PublicationDate_xml | – month: 03 year: 2020 text: 2020-03-02 day: 02 |
| PublicationDecade | 2020 |
| PublicationPlace | United States |
| PublicationPlace_xml | – name: United States |
| PublicationTitle | Optics express |
| PublicationTitleAlternate | Opt Express |
| PublicationYear | 2020 |
| References | Foi (oe-28-5-7360-R20) 2007; 16 Katkovnik (oe-28-5-7360-R11) 2012; 29 Zhang (oe-28-5-7360-R13) 2017; 7 Wang (oe-28-5-7360-R35) 2004; 13 Cai (oe-28-5-7360-R22) 2016; 25 Wang (oe-28-5-7360-R29) 2019; 27 Huang (oe-28-5-7360-R14) 2018; 26 Donoho (oe-28-5-7360-R10) 2006; 52 Zhai (oe-28-5-7360-R25) 2019; 58 Croton (oe-28-5-7360-R16) 2019; 27 Czajkowski (oe-28-5-7360-R36) 2018; 26 Veraart (oe-28-5-7360-R19) 2016; 76 Satat (oe-28-5-7360-R23) 2017; 25 Barbastathis (oe-28-5-7360-R21) 2019; 6 Welsh (oe-28-5-7360-R7) 2013; 21 Caramazza (oe-28-5-7360-R24) 2018; 8 Zhang (oe-28-5-7360-R3) 2015; 6 Peng (oe-28-5-7360-R8) 2018; 26 Katz (oe-28-5-7360-R12) 2009; 95 Münch (oe-28-5-7360-R17) 2009; 17 Jung (oe-28-5-7360-R18) 2010; 18 Zhang (oe-28-5-7360-R2) 2017; 25 Sun (oe-28-5-7360-R5) 2012; 20 Ferri (oe-28-5-7360-R4) 2010; 104 Sun (oe-28-5-7360-R6) 2013; 340 Gibbs (oe-28-5-7360-R15) 1898; 59 Zhao (oe-28-5-7360-R9) 2019; 44 Rizvi (oe-28-5-7360-R28) 2019; 19 Shapiro (oe-28-5-7360-R1) 2008; 78 Higham (oe-28-5-7360-R26) 2018; 8 He (oe-28-5-7360-R27) 2018; 8 |
| References_xml | – volume: 16 start-page: 1395 year: 2007 ident: oe-28-5-7360-R20 publication-title: IEEE Trans. Image Process. doi: 10.1109/TIP.2007.891788 – volume: 25 start-page: 19619 year: 2017 ident: oe-28-5-7360-R2 publication-title: Opt. Express doi: 10.1364/OE.25.019619 – volume: 27 start-page: 25560 year: 2019 ident: oe-28-5-7360-R29 publication-title: Opt. Express doi: 10.1364/OE.27.025560 – volume: 44 start-page: 3278 year: 2019 ident: oe-28-5-7360-R9 publication-title: Opt. Lett. doi: 10.1364/OL.44.003278 – volume: 26 start-page: 20009 year: 2018 ident: oe-28-5-7360-R36 publication-title: Opt. Express doi: 10.1364/OE.26.020009 – volume: 17 start-page: 8567 year: 2009 ident: oe-28-5-7360-R17 publication-title: Opt. Express doi: 10.1364/OE.17.008567 – volume: 8 start-page: 11945 year: 2018 ident: oe-28-5-7360-R24 publication-title: Sci. Rep. doi: 10.1038/s41598-018-30390-0 – volume: 52 start-page: 1289 year: 2006 ident: oe-28-5-7360-R10 publication-title: IEEE Trans. Inf. Theory doi: 10.1109/TIT.2006.871582 – volume: 25 start-page: 5187 year: 2016 ident: oe-28-5-7360-R22 publication-title: IEEE Trans. Image Process. doi: 10.1109/TIP.2016.2598681 – volume: 78 start-page: 061802 year: 2008 ident: oe-28-5-7360-R1 publication-title: Phys. Rev. A doi: 10.1103/PhysRevA.78.061802 – volume: 58 start-page: 8471 year: 2019 ident: oe-28-5-7360-R25 publication-title: Appl. Opt. doi: 10.1364/AO.58.008471 – volume: 6 start-page: 921 year: 2019 ident: oe-28-5-7360-R21 publication-title: Optica doi: 10.1364/OPTICA.6.000921 – volume: 21 start-page: 23068 year: 2013 ident: oe-28-5-7360-R7 publication-title: Opt. Express doi: 10.1364/OE.21.023068 – volume: 25 start-page: 17466 year: 2017 ident: oe-28-5-7360-R23 publication-title: Opt. Express doi: 10.1364/OE.25.017466 – volume: 7 start-page: 12029 year: 2017 ident: oe-28-5-7360-R13 publication-title: Sci. Rep. doi: 10.1038/s41598-017-12228-3 – volume: 19 start-page: 4190 year: 2019 ident: oe-28-5-7360-R28 publication-title: Sensors doi: 10.3390/s19194190 – volume: 26 start-page: 31094 year: 2018 ident: oe-28-5-7360-R8 publication-title: Opt. Express doi: 10.1364/OE.26.031094 – volume: 27 start-page: 14231 year: 2019 ident: oe-28-5-7360-R16 publication-title: Opt. Express doi: 10.1364/OE.27.014231 – volume: 20 start-page: 16892 year: 2012 ident: oe-28-5-7360-R5 publication-title: Opt. Express doi: 10.1364/OE.20.016892 – volume: 76 start-page: 301 year: 2016 ident: oe-28-5-7360-R19 publication-title: Magn. Reson. Med. doi: 10.1002/mrm.25866 – volume: 29 start-page: 1556 year: 2012 ident: oe-28-5-7360-R11 publication-title: J. Opt. Soc. Am. A doi: 10.1364/JOSAA.29.001556 – volume: 95 start-page: 131110 year: 2009 ident: oe-28-5-7360-R12 publication-title: Appl. Phys. Lett. doi: 10.1063/1.3238296 – volume: 8 start-page: 2369 year: 2018 ident: oe-28-5-7360-R26 publication-title: Sci. Rep. doi: 10.1038/s41598-018-20521-y – volume: 340 start-page: 844 year: 2013 ident: oe-28-5-7360-R6 publication-title: Science doi: 10.1126/science.1234454 – volume: 6 start-page: 6225 year: 2015 ident: oe-28-5-7360-R3 publication-title: Nat. Commun. doi: 10.1038/ncomms7225 – volume: 8 start-page: 6469 year: 2018 ident: oe-28-5-7360-R27 publication-title: Sci. Rep. doi: 10.1038/s41598-018-24731-2 – volume: 18 start-page: 7138 year: 2010 ident: oe-28-5-7360-R18 publication-title: Opt. Express doi: 10.1364/OE.18.007138 – volume: 59 start-page: 200 year: 1898 ident: oe-28-5-7360-R15 publication-title: Nature doi: 10.1038/059200b0 – volume: 13 start-page: 600 year: 2004 ident: oe-28-5-7360-R35 publication-title: IEEE T. Image Process. doi: 10.1109/TIP.2003.819861 – volume: 26 start-page: 16547 year: 2018 ident: oe-28-5-7360-R14 publication-title: Opt. Express doi: 10.1364/OE.26.016547 – volume: 104 start-page: 253603 year: 2010 ident: oe-28-5-7360-R4 publication-title: Phys. Rev. Lett. doi: 10.1103/PhysRevLett.104.253603 |
| SSID | ssj0014797 |
| Score | 2.532596 |
| Snippet | Undersampling in Fourier single pixel imaging (FSI) is often employed to reduce imaging time for real-time applications. However, the undersampled... |
| SourceID | proquest pubmed crossref |
| SourceType | Aggregation Database Index Database Enrichment Source |
| StartPage | 7360 |
| Title | Deringing and denoising in extremely under-sampled Fourier single pixel imaging |
| URI | https://www.ncbi.nlm.nih.gov/pubmed/32225966 https://www.proquest.com/docview/2384842870 |
| Volume | 28 |
| WOSCitedRecordID | wos000518435600117&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| journalDatabaseRights | – providerCode: PRVAON databaseName: DOAJ Directory of Open Access Journals customDbUrl: eissn: 1094-4087 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0014797 issn: 1094-4087 databaseCode: DOA dateStart: 19980101 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: 1094-4087 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0014797 issn: 1094-4087 databaseCode: M~E dateStart: 19970101 isFulltext: true titleUrlDefault: https://road.issn.org providerName: ISSN International Centre |
| link | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtV1bi9QwFA7uquCLeHe8DFF8EJbqTJM06aPoiCDuKKwwbyW3QmHslOnMMuuDv92TNM103RXWB1_CEJK25Hxzci7J-RB6RUplFS-nCafGJtSKLFG5lQklMMEoSbkSnmyCHx-LxSL_Gm6XtJ5OgNe12O3y5r-KGvpA2O7q7D-IOz4UOuA3CB1aEDu0VxL8B19csL97CGplVbXh4gooYhcOXJ559tt10kpXG9g4biVPXOfGLe1RU-3s8qj64QmMhtbrvPFFne2uiQc3fP3rn6dVF12WZp_T6FI6VQRODE1_ltXZdq_5_Lhv23oYfwBn0x3AGoQkp-Agghcatk17SV_Qs6kY4IkNlCYnHaXABW1OMgqrPZ-9IQL8ZbLfsvo0_R87WTxf6NN0GS3ms6KbeoCup5zlTnN_-TWLaSbKO_ad_nND6SmY-ja-9bzB8hcvxFsjJ3fQ7eBG4Hed-O-ia7a-h27647y6vY_mEQQYQIAjCHBV4wgCfA4EOIAAdyDAHgQ4gOAB-v5xdvL-UxKoMxJN0skmYbnWLLVMMaqlFhOrZUqYEQrsXQsuO_wLmVEcWi4NaHVpcmonOjNUu4JxnDxEh_Wqto8RZrLMcrADbSopNUqrfEqmpqS5LW1WUj5Cr_v1KXSoK-_oTZbFBSmM0Ms4tOmKqVw26EW_yAWoOpe_krVdbdsCrEsqfGZ-hB51qx8f4xKGDFz3J1d5xVN0a4_kZ-hws97a5-iGPt1U7XqMDvhCjH1wZuzh8hvbzn_J |
| 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=Deringing+and+denoising+in+extremely+under-sampled+Fourier+single+pixel+imaging&rft.jtitle=Optics+express&rft.au=Rizvi%2C+Saad&rft.au=Cao%2C+Jie&rft.au=Zhang%2C+Kaiyu&rft.au=Hao%2C+Qun&rft.date=2020-03-02&rft.issn=1094-4087&rft.eissn=1094-4087&rft.volume=28&rft.issue=5&rft.spage=7360&rft_id=info:doi/10.1364%2FOE.385233&rft.externalDBID=n%2Fa&rft.externalDocID=10_1364_OE_385233 |
| 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 |