IMAGE DECONVOLUTION USING COLOR PRIORS

Described are techniques for image deconvolution to deblur an image given a blur kernel. Localized color statistics derived from the image to be deblurred serve as a prior constraint during deconvolution. A pixel's color is formulated as a linear combination of the two most prevalent colors wit...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Hauptverfasser:	ZITNICK, CHARLES, LAWRENCE, SZELISKI, RICHARD, JOSHI, NEEL
Format:	Patent
Sprache:	eng ; fre ; ger
Schlagworte:	CALCULATING COMPUTING COUNTING IMAGE DATA PROCESSING OR GENERATION, IN GENERAL PHYSICS
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

container_end_page
container_issue
container_start_page
container_title
container_volume
creator	ZITNICK, CHARLES, LAWRENCE SZELISKI, RICHARD JOSHI, NEEL
description	Described are techniques for image deconvolution to deblur an image given a blur kernel. Localized color statistics derived from the image to be deblurred serve as a prior constraint during deconvolution. A pixel's color is formulated as a linear combination of the two most prevalent colors within a neighborhood of the pixel. This may be repeated for many or all pixels in an image. The linear combinations of the pixels serve as a two-color prior for deconvolving the blurred image. The two-color prior is responsive to the content of the image and it may decouple edge sharpness from edge strength.
format	Patent
fullrecord	<record><control><sourceid>epo_EVB</sourceid><recordid>TN_cdi_epo_espacenet_EP2291999A2</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>EP2291999A2</sourcerecordid><originalsourceid>FETCH-epo_espacenet_EP2291999A23</originalsourceid><addsrcrecordid>eNrjZFDz9HV0d1VwcXX29wvz9wkN8fT3UwgN9vRzV3D29_EPUggI8vQPCuZhYE1LzClO5YXS3AwKbq4hzh66qQX58anFBYnJqXmpJfGuAUZGloaWlpaORsZEKAEAlM4jeQ</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>patent</recordtype></control><display><type>patent</type><title>IMAGE DECONVOLUTION USING COLOR PRIORS</title><source>esp@cenet</source><creator>ZITNICK, CHARLES, LAWRENCE ; SZELISKI, RICHARD ; JOSHI, NEEL</creator><creatorcontrib>ZITNICK, CHARLES, LAWRENCE ; SZELISKI, RICHARD ; JOSHI, NEEL</creatorcontrib><description>Described are techniques for image deconvolution to deblur an image given a blur kernel. Localized color statistics derived from the image to be deblurred serve as a prior constraint during deconvolution. A pixel's color is formulated as a linear combination of the two most prevalent colors within a neighborhood of the pixel. This may be repeated for many or all pixels in an image. The linear combinations of the pixels serve as a two-color prior for deconvolving the blurred image. The two-color prior is responsive to the content of the image and it may decouple edge sharpness from edge strength.</description><language>eng ; fre ; ger</language><subject>CALCULATING ; COMPUTING ; COUNTING ; IMAGE DATA PROCESSING OR GENERATION, IN GENERAL ; PHYSICS</subject><creationdate>2011</creationdate><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&date=20110309&DB=EPODOC&CC=EP&NR=2291999A2$$EHTML$$P50$$Gepo$$Hfree_for_read</linktohtml><link.rule.ids>230,308,780,885,25564,76547</link.rule.ids><linktorsrc>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&date=20110309&DB=EPODOC&CC=EP&NR=2291999A2$$EView_record_in_European_Patent_Office$$FView_record_in_$$GEuropean_Patent_Office$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>ZITNICK, CHARLES, LAWRENCE</creatorcontrib><creatorcontrib>SZELISKI, RICHARD</creatorcontrib><creatorcontrib>JOSHI, NEEL</creatorcontrib><title>IMAGE DECONVOLUTION USING COLOR PRIORS</title><description>Described are techniques for image deconvolution to deblur an image given a blur kernel. Localized color statistics derived from the image to be deblurred serve as a prior constraint during deconvolution. A pixel's color is formulated as a linear combination of the two most prevalent colors within a neighborhood of the pixel. This may be repeated for many or all pixels in an image. The linear combinations of the pixels serve as a two-color prior for deconvolving the blurred image. The two-color prior is responsive to the content of the image and it may decouple edge sharpness from edge strength.</description><subject>CALCULATING</subject><subject>COMPUTING</subject><subject>COUNTING</subject><subject>IMAGE DATA PROCESSING OR GENERATION, IN GENERAL</subject><subject>PHYSICS</subject><fulltext>true</fulltext><rsrctype>patent</rsrctype><creationdate>2011</creationdate><recordtype>patent</recordtype><sourceid>EVB</sourceid><recordid>eNrjZFDz9HV0d1VwcXX29wvz9wkN8fT3UwgN9vRzV3D29_EPUggI8vQPCuZhYE1LzClO5YXS3AwKbq4hzh66qQX58anFBYnJqXmpJfGuAUZGloaWlpaORsZEKAEAlM4jeQ</recordid><startdate>20110309</startdate><enddate>20110309</enddate><creator>ZITNICK, CHARLES, LAWRENCE</creator><creator>SZELISKI, RICHARD</creator><creator>JOSHI, NEEL</creator><scope>EVB</scope></search><sort><creationdate>20110309</creationdate><title>IMAGE DECONVOLUTION USING COLOR PRIORS</title><author>ZITNICK, CHARLES, LAWRENCE ; SZELISKI, RICHARD ; JOSHI, NEEL</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-epo_espacenet_EP2291999A23</frbrgroupid><rsrctype>patents</rsrctype><prefilter>patents</prefilter><language>eng ; fre ; ger</language><creationdate>2011</creationdate><topic>CALCULATING</topic><topic>COMPUTING</topic><topic>COUNTING</topic><topic>IMAGE DATA PROCESSING OR GENERATION, IN GENERAL</topic><topic>PHYSICS</topic><toplevel>online_resources</toplevel><creatorcontrib>ZITNICK, CHARLES, LAWRENCE</creatorcontrib><creatorcontrib>SZELISKI, RICHARD</creatorcontrib><creatorcontrib>JOSHI, NEEL</creatorcontrib><collection>esp@cenet</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>ZITNICK, CHARLES, LAWRENCE</au><au>SZELISKI, RICHARD</au><au>JOSHI, NEEL</au><format>patent</format><genre>patent</genre><ristype>GEN</ristype><title>IMAGE DECONVOLUTION USING COLOR PRIORS</title><date>2011-03-09</date><risdate>2011</risdate><abstract>Described are techniques for image deconvolution to deblur an image given a blur kernel. Localized color statistics derived from the image to be deblurred serve as a prior constraint during deconvolution. A pixel's color is formulated as a linear combination of the two most prevalent colors within a neighborhood of the pixel. This may be repeated for many or all pixels in an image. The linear combinations of the pixels serve as a two-color prior for deconvolving the blurred image. The two-color prior is responsive to the content of the image and it may decouple edge sharpness from edge strength.</abstract><oa>free_for_read</oa></addata></record>
fulltext	fulltext_linktorsrc
identifier
ispartof
issn
language	eng ; fre ; ger
recordid	cdi_epo_espacenet_EP2291999A2
source	esp@cenet
subjects	CALCULATING COMPUTING COUNTING IMAGE DATA PROCESSING OR GENERATION, IN GENERAL PHYSICS
title	IMAGE DECONVOLUTION USING COLOR PRIORS
url	https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-30T03%3A00%3A57IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-epo_EVB&rft_val_fmt=info:ofi/fmt:kev:mtx:patent&rft.genre=patent&rft.au=ZITNICK,%20CHARLES,%20LAWRENCE&rft.date=2011-03-09&rft_id=info:doi/&rft_dat=%3Cepo_EVB%3EEP2291999A2%3C/epo_EVB%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rfr_iscdi=true