A Novel Texture Synthesis Based Algorithm for Object Removal in Photographs
Natural images and photographs sometimes may contain stains or undesired objects covering significant portions of the images. Inpainting is a method to fill in such portions using the information from the remaining area of the image. In this paper, we propose a novel photograph editing framework tha...
Gespeichert in:
| Veröffentlicht in: | Advances in Computer Science - ASIAN 2004. Higher-Level Decision Making 2004-01, p.248-258 |
|---|---|
| Hauptverfasser: | , , , |
| Format: | Artikel |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | 258 |
|---|---|
| container_issue | |
| container_start_page | 248 |
| container_title | Advances in Computer Science - ASIAN 2004. Higher-Level Decision Making |
| container_volume | |
| creator | Tang, Feng Ying, Yiting Wang, Jin Peng, Qunsheng |
| description | Natural images and photographs sometimes may contain stains or undesired objects covering significant portions of the images. Inpainting is a method to fill in such portions using the information from the remaining area of the image. In this paper, we propose a novel photograph editing framework that utilizes texture synthesis techniques. Major contributions of our algorithm are: 1) a constraint-based candidate patch searching method which limits the searching within neighboring region with similar texture; 2) a metric of Coherence Confidence for selecting the best fit candidate preventing error accumulation and propagation; 3) integration of graphcut optimization to make the seam visually invisible. Experiments show that our system can efficiently handle different cases especially large regions in complex background. |
| doi_str_mv | 10.1007/978-3-540-30502-6_18 |
| format | Article |
| fullrecord | <record><control><sourceid>pascalfrancis_sprin</sourceid><recordid>TN_cdi_pascalfrancis_primary_16398766</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>16398766</sourcerecordid><originalsourceid>FETCH-LOGICAL-c279t-f11f1c25a7f4a622ce474b0fce6dc419a1d0b6022d7c0d2e65f62e504abd88823</originalsourceid><addsrcrecordid>eNotkMlOwzAURc0kUUr_gIU3LA2eYjvLgphERRGUteU4dpOSxpUdKvr3JC1vc6V7j97iAHBF8A3BWN7mUiGGMo4RwxmmSGiijsAF65t9kR2DERGEIMZ4fgImPT9slGMl5SkY9RRFueTsHExSWuHhcsU4HoHXKXwLW9fAhfvtfqKDn7u2q1yqE7wzyZVw2ixDrLtqDX2IcF6snO3gh1uHrWlg3cL3KnRhGc2mSpfgzJsmucl_jsHX48Pi_hnN5k8v99MZslTmHfKEeGJpZqTnRlBqHZe8wN46UVpOckNKXAhMaSktLqkTmRfUZZibolRKUTYG14e_G5OsaXw0ra2T3sR6beJOE8FyJYXoOXrgUj-1Sxd1EcJ30gTrQavuNWmme1F6b1EPWtkf_-5lYA</addsrcrecordid><sourcetype>Index Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>A Novel Texture Synthesis Based Algorithm for Object Removal in Photographs</title><source>Springer Books</source><creator>Tang, Feng ; Ying, Yiting ; Wang, Jin ; Peng, Qunsheng</creator><contributor>Maher, Michael J.</contributor><creatorcontrib>Tang, Feng ; Ying, Yiting ; Wang, Jin ; Peng, Qunsheng ; Maher, Michael J.</creatorcontrib><description>Natural images and photographs sometimes may contain stains or undesired objects covering significant portions of the images. Inpainting is a method to fill in such portions using the information from the remaining area of the image. In this paper, we propose a novel photograph editing framework that utilizes texture synthesis techniques. Major contributions of our algorithm are: 1) a constraint-based candidate patch searching method which limits the searching within neighboring region with similar texture; 2) a metric of Coherence Confidence for selecting the best fit candidate preventing error accumulation and propagation; 3) integration of graphcut optimization to make the seam visually invisible. Experiments show that our system can efficiently handle different cases especially large regions in complex background.</description><identifier>ISSN: 0302-9743</identifier><identifier>ISBN: 9783540240877</identifier><identifier>ISBN: 354024087X</identifier><identifier>EISSN: 1611-3349</identifier><identifier>EISBN: 3540305025</identifier><identifier>EISBN: 9783540305026</identifier><identifier>DOI: 10.1007/978-3-540-30502-6_18</identifier><language>eng</language><publisher>Berlin, Heidelberg: Springer Berlin Heidelberg</publisher><subject>Applied sciences ; Candidate Pool ; Computer science; control theory; systems ; Error Match ; Exact sciences and technology ; Large Object ; Similar Texture ; Texture Synthesis</subject><ispartof>Advances in Computer Science - ASIAN 2004. Higher-Level Decision Making, 2004-01, p.248-258</ispartof><rights>Springer-Verlag Berlin Heidelberg 2004</rights><rights>2005 INIST-CNRS</rights><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c279t-f11f1c25a7f4a622ce474b0fce6dc419a1d0b6022d7c0d2e65f62e504abd88823</citedby></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktopdf>$$Uhttps://link.springer.com/content/pdf/10.1007/978-3-540-30502-6_18$$EPDF$$P50$$Gspringer$$H</linktopdf><linktohtml>$$Uhttps://link.springer.com/10.1007/978-3-540-30502-6_18$$EHTML$$P50$$Gspringer$$H</linktohtml><link.rule.ids>309,310,779,780,784,789,790,793,27925,38255,41442,42511</link.rule.ids><backlink>$$Uhttp://pascal-francis.inist.fr/vibad/index.php?action=getRecordDetail&idt=16398766$$DView record in Pascal Francis$$Hfree_for_read</backlink></links><search><contributor>Maher, Michael J.</contributor><creatorcontrib>Tang, Feng</creatorcontrib><creatorcontrib>Ying, Yiting</creatorcontrib><creatorcontrib>Wang, Jin</creatorcontrib><creatorcontrib>Peng, Qunsheng</creatorcontrib><title>A Novel Texture Synthesis Based Algorithm for Object Removal in Photographs</title><title>Advances in Computer Science - ASIAN 2004. Higher-Level Decision Making</title><description>Natural images and photographs sometimes may contain stains or undesired objects covering significant portions of the images. Inpainting is a method to fill in such portions using the information from the remaining area of the image. In this paper, we propose a novel photograph editing framework that utilizes texture synthesis techniques. Major contributions of our algorithm are: 1) a constraint-based candidate patch searching method which limits the searching within neighboring region with similar texture; 2) a metric of Coherence Confidence for selecting the best fit candidate preventing error accumulation and propagation; 3) integration of graphcut optimization to make the seam visually invisible. Experiments show that our system can efficiently handle different cases especially large regions in complex background.</description><subject>Applied sciences</subject><subject>Candidate Pool</subject><subject>Computer science; control theory; systems</subject><subject>Error Match</subject><subject>Exact sciences and technology</subject><subject>Large Object</subject><subject>Similar Texture</subject><subject>Texture Synthesis</subject><issn>0302-9743</issn><issn>1611-3349</issn><isbn>9783540240877</isbn><isbn>354024087X</isbn><isbn>3540305025</isbn><isbn>9783540305026</isbn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2004</creationdate><recordtype>article</recordtype><recordid>eNotkMlOwzAURc0kUUr_gIU3LA2eYjvLgphERRGUteU4dpOSxpUdKvr3JC1vc6V7j97iAHBF8A3BWN7mUiGGMo4RwxmmSGiijsAF65t9kR2DERGEIMZ4fgImPT9slGMl5SkY9RRFueTsHExSWuHhcsU4HoHXKXwLW9fAhfvtfqKDn7u2q1yqE7wzyZVw2ixDrLtqDX2IcF6snO3gh1uHrWlg3cL3KnRhGc2mSpfgzJsmucl_jsHX48Pi_hnN5k8v99MZslTmHfKEeGJpZqTnRlBqHZe8wN46UVpOckNKXAhMaSktLqkTmRfUZZibolRKUTYG14e_G5OsaXw0ra2T3sR6beJOE8FyJYXoOXrgUj-1Sxd1EcJ30gTrQavuNWmme1F6b1EPWtkf_-5lYA</recordid><startdate>20040101</startdate><enddate>20040101</enddate><creator>Tang, Feng</creator><creator>Ying, Yiting</creator><creator>Wang, Jin</creator><creator>Peng, Qunsheng</creator><general>Springer Berlin Heidelberg</general><general>Springer</general><scope>IQODW</scope></search><sort><creationdate>20040101</creationdate><title>A Novel Texture Synthesis Based Algorithm for Object Removal in Photographs</title><author>Tang, Feng ; Ying, Yiting ; Wang, Jin ; Peng, Qunsheng</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c279t-f11f1c25a7f4a622ce474b0fce6dc419a1d0b6022d7c0d2e65f62e504abd88823</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2004</creationdate><topic>Applied sciences</topic><topic>Candidate Pool</topic><topic>Computer science; control theory; systems</topic><topic>Error Match</topic><topic>Exact sciences and technology</topic><topic>Large Object</topic><topic>Similar Texture</topic><topic>Texture Synthesis</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Tang, Feng</creatorcontrib><creatorcontrib>Ying, Yiting</creatorcontrib><creatorcontrib>Wang, Jin</creatorcontrib><creatorcontrib>Peng, Qunsheng</creatorcontrib><collection>Pascal-Francis</collection><jtitle>Advances in Computer Science - ASIAN 2004. Higher-Level Decision Making</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Tang, Feng</au><au>Ying, Yiting</au><au>Wang, Jin</au><au>Peng, Qunsheng</au><au>Maher, Michael J.</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>A Novel Texture Synthesis Based Algorithm for Object Removal in Photographs</atitle><jtitle>Advances in Computer Science - ASIAN 2004. Higher-Level Decision Making</jtitle><date>2004-01-01</date><risdate>2004</risdate><spage>248</spage><epage>258</epage><pages>248-258</pages><issn>0302-9743</issn><eissn>1611-3349</eissn><isbn>9783540240877</isbn><isbn>354024087X</isbn><eisbn>3540305025</eisbn><eisbn>9783540305026</eisbn><abstract>Natural images and photographs sometimes may contain stains or undesired objects covering significant portions of the images. Inpainting is a method to fill in such portions using the information from the remaining area of the image. In this paper, we propose a novel photograph editing framework that utilizes texture synthesis techniques. Major contributions of our algorithm are: 1) a constraint-based candidate patch searching method which limits the searching within neighboring region with similar texture; 2) a metric of Coherence Confidence for selecting the best fit candidate preventing error accumulation and propagation; 3) integration of graphcut optimization to make the seam visually invisible. Experiments show that our system can efficiently handle different cases especially large regions in complex background.</abstract><cop>Berlin, Heidelberg</cop><pub>Springer Berlin Heidelberg</pub><doi>10.1007/978-3-540-30502-6_18</doi><tpages>11</tpages></addata></record> |
| fulltext | fulltext |
| identifier | ISSN: 0302-9743 |
| ispartof | Advances in Computer Science - ASIAN 2004. Higher-Level Decision Making, 2004-01, p.248-258 |
| issn | 0302-9743 1611-3349 |
| language | eng |
| recordid | cdi_pascalfrancis_primary_16398766 |
| source | Springer Books |
| subjects | Applied sciences Candidate Pool Computer science control theory systems Error Match Exact sciences and technology Large Object Similar Texture Texture Synthesis |
| title | A Novel Texture Synthesis Based Algorithm for Object Removal in Photographs |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-28T16%3A36%3A22IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-pascalfrancis_sprin&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=A%20Novel%20Texture%20Synthesis%20Based%20Algorithm%20for%20Object%20Removal%20in%20Photographs&rft.jtitle=Advances%20in%20Computer%20Science%20-%20ASIAN%202004.%20Higher-Level%20Decision%20Making&rft.au=Tang,%20Feng&rft.date=2004-01-01&rft.spage=248&rft.epage=258&rft.pages=248-258&rft.issn=0302-9743&rft.eissn=1611-3349&rft.isbn=9783540240877&rft.isbn_list=354024087X&rft_id=info:doi/10.1007/978-3-540-30502-6_18&rft_dat=%3Cpascalfrancis_sprin%3E16398766%3C/pascalfrancis_sprin%3E%3Curl%3E%3C/url%3E&rft.eisbn=3540305025&rft.eisbn_list=9783540305026&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rfr_iscdi=true |