Improved characteristic similarity image quality evaluating method

The invention relates to an improved characteristic similarity image quality evaluating method, and belongs to the technical field of digital image processing. The method includes the steps that an original image and a distorted image are input first, phase equalizations of the two images are acquir...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: YI SANLI, MIAO YING
Format: Patent
Sprache:eng
Schlagworte:
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 YI SANLI
MIAO YING
description The invention relates to an improved characteristic similarity image quality evaluating method, and belongs to the technical field of digital image processing. The method includes the steps that an original image and a distorted image are input first, phase equalizations of the two images are acquired respectively, and then the characteristic similarity of the images is obtained through the phase equalizations of the two images; afterwards, gradient images of the two images are acquired respectively, a brightness comparison function, a contrast ratio comparison function and a correlation coefficient comparison function of the two images are obtained through the gradient images, and then the brightness comparison function, the contrast ratio comparison function and the correlation coefficient comparison function are combined so that the gradient similarity of the images can be obtained; at last, the characteristic similarity of the images and the gradient similarity of the images are combined, and accordingly the distorted image quality evaluating result is obtained. The method has the advantage of meeting the requirement of a human vision system and the advantage of effectively recognizing the image edges, and more sensitivity to distortion caused by motion blurs is achieved.
format Patent
fullrecord <record><control><sourceid>epo_EVB</sourceid><recordid>TN_cdi_epo_espacenet_CN105205820A</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>CN105205820A</sourcerecordid><originalsourceid>FETCH-epo_espacenet_CN105205820A3</originalsourceid><addsrcrecordid>eNrjZHDyzC0oyi9LTVFIzkgsSkwuSS3KLC7JTFYozszNzEksyiypVMjMTUxPVSgsTcwB8VLLEnNKE0sy89IVclNLMvJTeBhY0xJzilN5oTQ3g6Kba4izh25qQX58anFBYnJqXmpJvLOfoYGpkYGphZGBozExagCx8jLq</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>patent</recordtype></control><display><type>patent</type><title>Improved characteristic similarity image quality evaluating method</title><source>esp@cenet</source><creator>YI SANLI ; MIAO YING</creator><creatorcontrib>YI SANLI ; MIAO YING</creatorcontrib><description>The invention relates to an improved characteristic similarity image quality evaluating method, and belongs to the technical field of digital image processing. The method includes the steps that an original image and a distorted image are input first, phase equalizations of the two images are acquired respectively, and then the characteristic similarity of the images is obtained through the phase equalizations of the two images; afterwards, gradient images of the two images are acquired respectively, a brightness comparison function, a contrast ratio comparison function and a correlation coefficient comparison function of the two images are obtained through the gradient images, and then the brightness comparison function, the contrast ratio comparison function and the correlation coefficient comparison function are combined so that the gradient similarity of the images can be obtained; at last, the characteristic similarity of the images and the gradient similarity of the images are combined, and accordingly the distorted image quality evaluating result is obtained. The method has the advantage of meeting the requirement of a human vision system and the advantage of effectively recognizing the image edges, and more sensitivity to distortion caused by motion blurs is achieved.</description><language>eng</language><subject>CALCULATING ; COMPUTING ; COUNTING ; IMAGE DATA PROCESSING OR GENERATION, IN GENERAL ; PHYSICS</subject><creationdate>2015</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&amp;date=20151230&amp;DB=EPODOC&amp;CC=CN&amp;NR=105205820A$$EHTML$$P50$$Gepo$$Hfree_for_read</linktohtml><link.rule.ids>230,308,776,881,25542,76516</link.rule.ids><linktorsrc>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&amp;date=20151230&amp;DB=EPODOC&amp;CC=CN&amp;NR=105205820A$$EView_record_in_European_Patent_Office$$FView_record_in_$$GEuropean_Patent_Office$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>YI SANLI</creatorcontrib><creatorcontrib>MIAO YING</creatorcontrib><title>Improved characteristic similarity image quality evaluating method</title><description>The invention relates to an improved characteristic similarity image quality evaluating method, and belongs to the technical field of digital image processing. The method includes the steps that an original image and a distorted image are input first, phase equalizations of the two images are acquired respectively, and then the characteristic similarity of the images is obtained through the phase equalizations of the two images; afterwards, gradient images of the two images are acquired respectively, a brightness comparison function, a contrast ratio comparison function and a correlation coefficient comparison function of the two images are obtained through the gradient images, and then the brightness comparison function, the contrast ratio comparison function and the correlation coefficient comparison function are combined so that the gradient similarity of the images can be obtained; at last, the characteristic similarity of the images and the gradient similarity of the images are combined, and accordingly the distorted image quality evaluating result is obtained. The method has the advantage of meeting the requirement of a human vision system and the advantage of effectively recognizing the image edges, and more sensitivity to distortion caused by motion blurs is achieved.</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>2015</creationdate><recordtype>patent</recordtype><sourceid>EVB</sourceid><recordid>eNrjZHDyzC0oyi9LTVFIzkgsSkwuSS3KLC7JTFYozszNzEksyiypVMjMTUxPVSgsTcwB8VLLEnNKE0sy89IVclNLMvJTeBhY0xJzilN5oTQ3g6Kba4izh25qQX58anFBYnJqXmpJvLOfoYGpkYGphZGBozExagCx8jLq</recordid><startdate>20151230</startdate><enddate>20151230</enddate><creator>YI SANLI</creator><creator>MIAO YING</creator><scope>EVB</scope></search><sort><creationdate>20151230</creationdate><title>Improved characteristic similarity image quality evaluating method</title><author>YI SANLI ; MIAO YING</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-epo_espacenet_CN105205820A3</frbrgroupid><rsrctype>patents</rsrctype><prefilter>patents</prefilter><language>eng</language><creationdate>2015</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>YI SANLI</creatorcontrib><creatorcontrib>MIAO YING</creatorcontrib><collection>esp@cenet</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>YI SANLI</au><au>MIAO YING</au><format>patent</format><genre>patent</genre><ristype>GEN</ristype><title>Improved characteristic similarity image quality evaluating method</title><date>2015-12-30</date><risdate>2015</risdate><abstract>The invention relates to an improved characteristic similarity image quality evaluating method, and belongs to the technical field of digital image processing. The method includes the steps that an original image and a distorted image are input first, phase equalizations of the two images are acquired respectively, and then the characteristic similarity of the images is obtained through the phase equalizations of the two images; afterwards, gradient images of the two images are acquired respectively, a brightness comparison function, a contrast ratio comparison function and a correlation coefficient comparison function of the two images are obtained through the gradient images, and then the brightness comparison function, the contrast ratio comparison function and the correlation coefficient comparison function are combined so that the gradient similarity of the images can be obtained; at last, the characteristic similarity of the images and the gradient similarity of the images are combined, and accordingly the distorted image quality evaluating result is obtained. The method has the advantage of meeting the requirement of a human vision system and the advantage of effectively recognizing the image edges, and more sensitivity to distortion caused by motion blurs is achieved.</abstract><oa>free_for_read</oa></addata></record>
fulltext fulltext_linktorsrc
identifier
ispartof
issn
language eng
recordid cdi_epo_espacenet_CN105205820A
source esp@cenet
subjects CALCULATING
COMPUTING
COUNTING
IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
PHYSICS
title Improved characteristic similarity image quality evaluating method
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-02-21T15%3A19%3A03IST&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=YI%20SANLI&rft.date=2015-12-30&rft_id=info:doi/&rft_dat=%3Cepo_EVB%3ECN105205820A%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