A super-resolution method based on local sparse and global gradient
Super-resolution methods based on sparse easily lead to over-smoothing at the edges of reconstructed image. A novel super-resolution method based on local sparse and global gradient is proposed to solve the problem. First, it represents the input low-resolution (LR) image patches with sparse coeffic...
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 | 265 |
|---|---|
| container_issue | |
| container_start_page | 261 |
| container_title | |
| container_volume | |
| creator | Kebin Huang Ruimin Hu Zhen Han Feng Wang |
| description | Super-resolution methods based on sparse easily lead to over-smoothing at the edges of reconstructed image. A novel super-resolution method based on local sparse and global gradient is proposed to solve the problem. First, it represents the input low-resolution (LR) image patches with sparse coefficients and LR over-complete dictionary. Then it maps the coefficients to high resolution (HR) over-complete dictionary and reconstructs the HR texture. At last, it enhances the main edge using global natural image statistics' prior information and merges it together with the texture. By using the local sparse representation and global gradient transformation, it can obtain the result image with clean texture and clear edge. Experimental results validate the proposed method, both in subjective and objective quality. |
| doi_str_mv | 10.1109/IASP.2011.6109043 |
| format | Conference Proceeding |
| fullrecord | <record><control><sourceid>ieee_6IE</sourceid><recordid>TN_cdi_ieee_primary_6109043</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>6109043</ieee_id><sourcerecordid>6109043</sourcerecordid><originalsourceid>FETCH-LOGICAL-i90t-a446ecd6be486938be2f6acf087f7e189e8bc6580a51c083663c40b738e8002c3</originalsourceid><addsrcrecordid>eNotkE9LxDAUxCMquK79AOIlX6D1JWnTl2Mp_llYUHDvS5K-rpVuW5LuwW9vwc5l-A3DHIaxRwGZEGCed9XXZyZBiEwvCLm6YvdCC4k5osBrlpgSVy6NvGEbKQqdLn24Y0mMP7BIayMBN6yueLxMFNJAcewvczcO_Ezz99hwZyM1fOF-9LbncbIhErdDw0_96JbkFGzT0TA_sNvW9pGS1bfs8PpyqN_T_cfbrq72aWdgTm2ea_KNdpSjNgodyVZb3wKWbUkCDaHzukCwhfCASmvlc3ClQkIA6dWWPf3PdkR0nEJ3tuH3uF6g_gCIvEzA</addsrcrecordid><sourcetype>Publisher</sourcetype><iscdi>true</iscdi><recordtype>conference_proceeding</recordtype></control><display><type>conference_proceeding</type><title>A super-resolution method based on local sparse and global gradient</title><source>IEEE Electronic Library (IEL) Conference Proceedings</source><creator>Kebin Huang ; Ruimin Hu ; Zhen Han ; Feng Wang</creator><creatorcontrib>Kebin Huang ; Ruimin Hu ; Zhen Han ; Feng Wang</creatorcontrib><description>Super-resolution methods based on sparse easily lead to over-smoothing at the edges of reconstructed image. A novel super-resolution method based on local sparse and global gradient is proposed to solve the problem. First, it represents the input low-resolution (LR) image patches with sparse coefficients and LR over-complete dictionary. Then it maps the coefficients to high resolution (HR) over-complete dictionary and reconstructs the HR texture. At last, it enhances the main edge using global natural image statistics' prior information and merges it together with the texture. By using the local sparse representation and global gradient transformation, it can obtain the result image with clean texture and clear edge. Experimental results validate the proposed method, both in subjective and objective quality.</description><identifier>ISSN: 2156-0110</identifier><identifier>ISBN: 9781612848792</identifier><identifier>ISBN: 1612848796</identifier><identifier>EISBN: 1612848818</identifier><identifier>EISBN: 9781612848815</identifier><identifier>DOI: 10.1109/IASP.2011.6109043</identifier><language>eng</language><publisher>IEEE</publisher><subject>Dictionaries ; global gradient ; Image edge detection ; Image reconstruction ; Image resolution ; Interpolation ; Signal resolution ; sparse representation ; super-resolution ; Training</subject><ispartof>2011 International Conference on Image Analysis and Signal Processing, 2011, p.261-265</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/6109043$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>310,311,781,785,790,791,2059,27929,54924</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/6109043$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc></links><search><creatorcontrib>Kebin Huang</creatorcontrib><creatorcontrib>Ruimin Hu</creatorcontrib><creatorcontrib>Zhen Han</creatorcontrib><creatorcontrib>Feng Wang</creatorcontrib><title>A super-resolution method based on local sparse and global gradient</title><title>2011 International Conference on Image Analysis and Signal Processing</title><addtitle>IASP</addtitle><description>Super-resolution methods based on sparse easily lead to over-smoothing at the edges of reconstructed image. A novel super-resolution method based on local sparse and global gradient is proposed to solve the problem. First, it represents the input low-resolution (LR) image patches with sparse coefficients and LR over-complete dictionary. Then it maps the coefficients to high resolution (HR) over-complete dictionary and reconstructs the HR texture. At last, it enhances the main edge using global natural image statistics' prior information and merges it together with the texture. By using the local sparse representation and global gradient transformation, it can obtain the result image with clean texture and clear edge. Experimental results validate the proposed method, both in subjective and objective quality.</description><subject>Dictionaries</subject><subject>global gradient</subject><subject>Image edge detection</subject><subject>Image reconstruction</subject><subject>Image resolution</subject><subject>Interpolation</subject><subject>Signal resolution</subject><subject>sparse representation</subject><subject>super-resolution</subject><subject>Training</subject><issn>2156-0110</issn><isbn>9781612848792</isbn><isbn>1612848796</isbn><isbn>1612848818</isbn><isbn>9781612848815</isbn><fulltext>true</fulltext><rsrctype>conference_proceeding</rsrctype><creationdate>2011</creationdate><recordtype>conference_proceeding</recordtype><sourceid>6IE</sourceid><sourceid>RIE</sourceid><recordid>eNotkE9LxDAUxCMquK79AOIlX6D1JWnTl2Mp_llYUHDvS5K-rpVuW5LuwW9vwc5l-A3DHIaxRwGZEGCed9XXZyZBiEwvCLm6YvdCC4k5osBrlpgSVy6NvGEbKQqdLn24Y0mMP7BIayMBN6yueLxMFNJAcewvczcO_Ezz99hwZyM1fOF-9LbncbIhErdDw0_96JbkFGzT0TA_sNvW9pGS1bfs8PpyqN_T_cfbrq72aWdgTm2ea_KNdpSjNgodyVZb3wKWbUkCDaHzukCwhfCASmvlc3ClQkIA6dWWPf3PdkR0nEJ3tuH3uF6g_gCIvEzA</recordid><startdate>201110</startdate><enddate>201110</enddate><creator>Kebin Huang</creator><creator>Ruimin Hu</creator><creator>Zhen Han</creator><creator>Feng Wang</creator><general>IEEE</general><scope>6IE</scope><scope>6IL</scope><scope>CBEJK</scope><scope>RIE</scope><scope>RIL</scope></search><sort><creationdate>201110</creationdate><title>A super-resolution method based on local sparse and global gradient</title><author>Kebin Huang ; Ruimin Hu ; Zhen Han ; Feng Wang</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-i90t-a446ecd6be486938be2f6acf087f7e189e8bc6580a51c083663c40b738e8002c3</frbrgroupid><rsrctype>conference_proceedings</rsrctype><prefilter>conference_proceedings</prefilter><language>eng</language><creationdate>2011</creationdate><topic>Dictionaries</topic><topic>global gradient</topic><topic>Image edge detection</topic><topic>Image reconstruction</topic><topic>Image resolution</topic><topic>Interpolation</topic><topic>Signal resolution</topic><topic>sparse representation</topic><topic>super-resolution</topic><topic>Training</topic><toplevel>online_resources</toplevel><creatorcontrib>Kebin Huang</creatorcontrib><creatorcontrib>Ruimin Hu</creatorcontrib><creatorcontrib>Zhen Han</creatorcontrib><creatorcontrib>Feng Wang</creatorcontrib><collection>IEEE Electronic Library (IEL) Conference Proceedings</collection><collection>IEEE Proceedings Order Plan All Online (POP All Online) 1998-present by volume</collection><collection>IEEE Xplore All Conference Proceedings</collection><collection>IEEE Electronic Library (IEL)</collection><collection>IEEE Proceedings Order Plans (POP All) 1998-Present</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Kebin Huang</au><au>Ruimin Hu</au><au>Zhen Han</au><au>Feng Wang</au><format>book</format><genre>proceeding</genre><ristype>CONF</ristype><atitle>A super-resolution method based on local sparse and global gradient</atitle><btitle>2011 International Conference on Image Analysis and Signal Processing</btitle><stitle>IASP</stitle><date>2011-10</date><risdate>2011</risdate><spage>261</spage><epage>265</epage><pages>261-265</pages><issn>2156-0110</issn><isbn>9781612848792</isbn><isbn>1612848796</isbn><eisbn>1612848818</eisbn><eisbn>9781612848815</eisbn><abstract>Super-resolution methods based on sparse easily lead to over-smoothing at the edges of reconstructed image. A novel super-resolution method based on local sparse and global gradient is proposed to solve the problem. First, it represents the input low-resolution (LR) image patches with sparse coefficients and LR over-complete dictionary. Then it maps the coefficients to high resolution (HR) over-complete dictionary and reconstructs the HR texture. At last, it enhances the main edge using global natural image statistics' prior information and merges it together with the texture. By using the local sparse representation and global gradient transformation, it can obtain the result image with clean texture and clear edge. Experimental results validate the proposed method, both in subjective and objective quality.</abstract><pub>IEEE</pub><doi>10.1109/IASP.2011.6109043</doi><tpages>5</tpages></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | ISSN: 2156-0110 |
| ispartof | 2011 International Conference on Image Analysis and Signal Processing, 2011, p.261-265 |
| issn | 2156-0110 |
| language | eng |
| recordid | cdi_ieee_primary_6109043 |
| source | IEEE Electronic Library (IEL) Conference Proceedings |
| subjects | Dictionaries global gradient Image edge detection Image reconstruction Image resolution Interpolation Signal resolution sparse representation super-resolution Training |
| title | A super-resolution method based on local sparse and global gradient |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-16T17%3A16%3A54IST&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=A%20super-resolution%20method%20based%20on%20local%20sparse%20and%20global%20gradient&rft.btitle=2011%20International%20Conference%20on%20Image%20Analysis%20and%20Signal%20Processing&rft.au=Kebin%20Huang&rft.date=2011-10&rft.spage=261&rft.epage=265&rft.pages=261-265&rft.issn=2156-0110&rft.isbn=9781612848792&rft.isbn_list=1612848796&rft_id=info:doi/10.1109/IASP.2011.6109043&rft_dat=%3Cieee_6IE%3E6109043%3C/ieee_6IE%3E%3Curl%3E%3C/url%3E&rft.eisbn=1612848818&rft.eisbn_list=9781612848815&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rft_ieee_id=6109043&rfr_iscdi=true |