Texture preserving multi frame super resolution with spatially varying image prior
This paper proposes a new maximum a posteriori (MAP) based super-resolution (SR) image reconstruction method targeting edges and textures in images. Unlike conventional MAP based SR image reconstruction methods a spatially varying image prior is employed which is updated according to the frequency c...
Gespeichert in:
| Hauptverfasser: | , |
|---|---|
| Format: | Tagungsbericht |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext bestellen |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | 2208 |
|---|---|
| container_issue | |
| container_start_page | 2205 |
| container_title | |
| container_volume | |
| creator | Turgay, E. Akar, G. B. |
| description | This paper proposes a new maximum a posteriori (MAP) based super-resolution (SR) image reconstruction method targeting edges and textures in images. Unlike conventional MAP based SR image reconstruction methods a spatially varying image prior is employed which is updated according to the frequency content of the reconstructed image at each iteration at different locations. Two alternative methods based on discrete cosine transforms (DCT) and Gabor filters are proposed for determining the image prior. The proposed method is validated through simulations and real experiments which clearly demonstrates significant visual improvements especially on edges and textures compared to state-of-the-art SR methods. |
| doi_str_mv | 10.1109/ICIP.2012.6467332 |
| format | Conference Proceeding |
| fullrecord | <record><control><sourceid>ieee_6IE</sourceid><recordid>TN_cdi_ieee_primary_6467332</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>6467332</ieee_id><sourcerecordid>6467332</sourcerecordid><originalsourceid>FETCH-LOGICAL-i175t-4a1b52d88c5cabba690e6572bec60cd6ef79f7266c0c300d6d7e2c062bf27e6e3</originalsourceid><addsrcrecordid>eNo1kNtOwzAQRM1Noi39AMSLfyDFXseXPKKIS6RKIFSeK8fZFKOkqRyn0L8nFeVpNBrt2dEQcsvZgnOW3Rd58bYAxmGhUqWFgDMyz7ThRwNy9OdkAsLwxMg0uyDT_yDll2TCJUCSGsOuybTvvxgbQYJPyPsKf-IQkO4C9hj2fruh7dBET-tgW6T9sMNAx6xrhui7Lf328ZP2Oxu9bZoD3dtwON741m6OEN-FG3JV26bH-Uln5OPpcZW_JMvX5yJ_WCaeaxmT1PJSQmWMk86WpVUZQyU1lOgUc5XCWme1BqUcc4KxSlUawTEFZQ0aFYoZufvjekRcj6_bscv6tI34BfdfVgc</addsrcrecordid><sourcetype>Publisher</sourcetype><iscdi>true</iscdi><recordtype>conference_proceeding</recordtype></control><display><type>conference_proceeding</type><title>Texture preserving multi frame super resolution with spatially varying image prior</title><source>IEEE Electronic Library (IEL) Conference Proceedings</source><creator>Turgay, E. ; Akar, G. B.</creator><creatorcontrib>Turgay, E. ; Akar, G. B.</creatorcontrib><description>This paper proposes a new maximum a posteriori (MAP) based super-resolution (SR) image reconstruction method targeting edges and textures in images. Unlike conventional MAP based SR image reconstruction methods a spatially varying image prior is employed which is updated according to the frequency content of the reconstructed image at each iteration at different locations. Two alternative methods based on discrete cosine transforms (DCT) and Gabor filters are proposed for determining the image prior. The proposed method is validated through simulations and real experiments which clearly demonstrates significant visual improvements especially on edges and textures compared to state-of-the-art SR methods.</description><identifier>ISSN: 1522-4880</identifier><identifier>ISBN: 1467325341</identifier><identifier>ISBN: 9781467325349</identifier><identifier>EISSN: 2381-8549</identifier><identifier>EISBN: 9781467325332</identifier><identifier>EISBN: 1467325325</identifier><identifier>EISBN: 9781467325325</identifier><identifier>EISBN: 1467325333</identifier><identifier>DOI: 10.1109/ICIP.2012.6467332</identifier><language>eng</language><publisher>IEEE</publisher><subject>Bayesian ; DCT ; Discrete cosine transforms ; Estimation ; Gabor ; Image edge detection ; Image reconstruction ; Image resolution ; Image restoration ; PSNR ; Super Resolution ; Texture</subject><ispartof>2012 19th IEEE International Conference on Image Processing, 2012, p.2205-2208</ispartof><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://ieeexplore.ieee.org/document/6467332$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>309,310,780,784,789,790,2058,27925,54920</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/6467332$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc></links><search><creatorcontrib>Turgay, E.</creatorcontrib><creatorcontrib>Akar, G. B.</creatorcontrib><title>Texture preserving multi frame super resolution with spatially varying image prior</title><title>2012 19th IEEE International Conference on Image Processing</title><addtitle>ICIP</addtitle><description>This paper proposes a new maximum a posteriori (MAP) based super-resolution (SR) image reconstruction method targeting edges and textures in images. Unlike conventional MAP based SR image reconstruction methods a spatially varying image prior is employed which is updated according to the frequency content of the reconstructed image at each iteration at different locations. Two alternative methods based on discrete cosine transforms (DCT) and Gabor filters are proposed for determining the image prior. The proposed method is validated through simulations and real experiments which clearly demonstrates significant visual improvements especially on edges and textures compared to state-of-the-art SR methods.</description><subject>Bayesian</subject><subject>DCT</subject><subject>Discrete cosine transforms</subject><subject>Estimation</subject><subject>Gabor</subject><subject>Image edge detection</subject><subject>Image reconstruction</subject><subject>Image resolution</subject><subject>Image restoration</subject><subject>PSNR</subject><subject>Super Resolution</subject><subject>Texture</subject><issn>1522-4880</issn><issn>2381-8549</issn><isbn>1467325341</isbn><isbn>9781467325349</isbn><isbn>9781467325332</isbn><isbn>1467325325</isbn><isbn>9781467325325</isbn><isbn>1467325333</isbn><fulltext>true</fulltext><rsrctype>conference_proceeding</rsrctype><creationdate>2012</creationdate><recordtype>conference_proceeding</recordtype><sourceid>6IE</sourceid><sourceid>RIE</sourceid><recordid>eNo1kNtOwzAQRM1Noi39AMSLfyDFXseXPKKIS6RKIFSeK8fZFKOkqRyn0L8nFeVpNBrt2dEQcsvZgnOW3Rd58bYAxmGhUqWFgDMyz7ThRwNy9OdkAsLwxMg0uyDT_yDll2TCJUCSGsOuybTvvxgbQYJPyPsKf-IQkO4C9hj2fruh7dBET-tgW6T9sMNAx6xrhui7Lf328ZP2Oxu9bZoD3dtwON741m6OEN-FG3JV26bH-Uln5OPpcZW_JMvX5yJ_WCaeaxmT1PJSQmWMk86WpVUZQyU1lOgUc5XCWme1BqUcc4KxSlUawTEFZQ0aFYoZufvjekRcj6_bscv6tI34BfdfVgc</recordid><startdate>201209</startdate><enddate>201209</enddate><creator>Turgay, E.</creator><creator>Akar, G. B.</creator><general>IEEE</general><scope>6IE</scope><scope>6IH</scope><scope>CBEJK</scope><scope>RIE</scope><scope>RIO</scope></search><sort><creationdate>201209</creationdate><title>Texture preserving multi frame super resolution with spatially varying image prior</title><author>Turgay, E. ; Akar, G. B.</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-i175t-4a1b52d88c5cabba690e6572bec60cd6ef79f7266c0c300d6d7e2c062bf27e6e3</frbrgroupid><rsrctype>conference_proceedings</rsrctype><prefilter>conference_proceedings</prefilter><language>eng</language><creationdate>2012</creationdate><topic>Bayesian</topic><topic>DCT</topic><topic>Discrete cosine transforms</topic><topic>Estimation</topic><topic>Gabor</topic><topic>Image edge detection</topic><topic>Image reconstruction</topic><topic>Image resolution</topic><topic>Image restoration</topic><topic>PSNR</topic><topic>Super Resolution</topic><topic>Texture</topic><toplevel>online_resources</toplevel><creatorcontrib>Turgay, E.</creatorcontrib><creatorcontrib>Akar, G. B.</creatorcontrib><collection>IEEE Electronic Library (IEL) Conference Proceedings</collection><collection>IEEE Proceedings Order Plan (POP) 1998-present by volume</collection><collection>IEEE Xplore All Conference Proceedings</collection><collection>IEEE Electronic Library (IEL)</collection><collection>IEEE Proceedings Order Plans (POP) 1998-present</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Turgay, E.</au><au>Akar, G. B.</au><format>book</format><genre>proceeding</genre><ristype>CONF</ristype><atitle>Texture preserving multi frame super resolution with spatially varying image prior</atitle><btitle>2012 19th IEEE International Conference on Image Processing</btitle><stitle>ICIP</stitle><date>2012-09</date><risdate>2012</risdate><spage>2205</spage><epage>2208</epage><pages>2205-2208</pages><issn>1522-4880</issn><eissn>2381-8549</eissn><isbn>1467325341</isbn><isbn>9781467325349</isbn><eisbn>9781467325332</eisbn><eisbn>1467325325</eisbn><eisbn>9781467325325</eisbn><eisbn>1467325333</eisbn><abstract>This paper proposes a new maximum a posteriori (MAP) based super-resolution (SR) image reconstruction method targeting edges and textures in images. Unlike conventional MAP based SR image reconstruction methods a spatially varying image prior is employed which is updated according to the frequency content of the reconstructed image at each iteration at different locations. Two alternative methods based on discrete cosine transforms (DCT) and Gabor filters are proposed for determining the image prior. The proposed method is validated through simulations and real experiments which clearly demonstrates significant visual improvements especially on edges and textures compared to state-of-the-art SR methods.</abstract><pub>IEEE</pub><doi>10.1109/ICIP.2012.6467332</doi><tpages>4</tpages></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | ISSN: 1522-4880 |
| ispartof | 2012 19th IEEE International Conference on Image Processing, 2012, p.2205-2208 |
| issn | 1522-4880 2381-8549 |
| language | eng |
| recordid | cdi_ieee_primary_6467332 |
| source | IEEE Electronic Library (IEL) Conference Proceedings |
| subjects | Bayesian DCT Discrete cosine transforms Estimation Gabor Image edge detection Image reconstruction Image resolution Image restoration PSNR Super Resolution Texture |
| title | Texture preserving multi frame super resolution with spatially varying image prior |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-26T02%3A54%3A24IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-ieee_6IE&rft_val_fmt=info:ofi/fmt:kev:mtx:book&rft.genre=proceeding&rft.atitle=Texture%20preserving%20multi%20frame%20super%20resolution%20with%20spatially%20varying%20image%20prior&rft.btitle=2012%2019th%20IEEE%20International%20Conference%20on%20Image%20Processing&rft.au=Turgay,%20E.&rft.date=2012-09&rft.spage=2205&rft.epage=2208&rft.pages=2205-2208&rft.issn=1522-4880&rft.eissn=2381-8549&rft.isbn=1467325341&rft.isbn_list=9781467325349&rft_id=info:doi/10.1109/ICIP.2012.6467332&rft_dat=%3Cieee_6IE%3E6467332%3C/ieee_6IE%3E%3Curl%3E%3C/url%3E&rft.eisbn=9781467325332&rft.eisbn_list=1467325325&rft.eisbn_list=9781467325325&rft.eisbn_list=1467325333&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rft_ieee_id=6467332&rfr_iscdi=true |