Salient Region Detection Algorithm via KL Divergence and Multi-scale Merging

A new salient region detection algorithm is proposed via KL divergence between color probability distributions of super-pixels and merging multi-scale saliency maps. Firstly, multi-scale super-pixel segmentations of an input image are computed. In each segmentation scale, an undirected close-loop co...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Dian zi yu xin xi xue bao = Journal of electronics & information technology 2016-07, Vol.38 (7), p.1594-1601
Hauptverfasser: Luo, Huilan, Wan, Chengtao, Kong, Fansheng
Format: Artikel
Sprache:chi
Schlagworte:
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page 1601
container_issue 7
container_start_page 1594
container_title Dian zi yu xin xi xue bao = Journal of electronics & information technology
container_volume 38
creator Luo, Huilan
Wan, Chengtao
Kong, Fansheng
description A new salient region detection algorithm is proposed via KL divergence between color probability distributions of super-pixels and merging multi-scale saliency maps. Firstly, multi-scale super-pixel segmentations of an input image are computed. In each segmentation scale, an undirected close-loop connected graph is constructed, in which nodes are the super-pixels and the adjacent regions are expanded reasonably relying on the total number of super-pixels. Then, all the color values in each super-pixel are clustered in terms of their discriminative power to get the statistical probability distribution of the cluster labels for each super-pixel. Next, the edges between all adjacent super-pixel pairs are weighted with the harmonic-mean of KL divergence of their probability distributions, and then the multi-scale saliency maps are calculated according to boundary connectivity and region contrast. The final saliency map is obtained by calculating and optimizing the mean map of all the saliency maps with different
doi_str_mv 10.11999/JEIT151145
format Article
fullrecord <record><control><sourceid>proquest</sourceid><recordid>TN_cdi_proquest_miscellaneous_1864552625</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>1864552625</sourcerecordid><originalsourceid>FETCH-LOGICAL-p103t-d512ccd672d967606b84dcd864797bee4bf0b2415b07baee6701c7bf2e1182ba3</originalsourceid><addsrcrecordid>eNotjrFOwzAURT2ARFU68QMeWQJ-TmzHY9UWKKRCgjJXtvMSLLlJiZ1-P6lgukc60tEl5A7YA4DW-vF1s92DACjEFZkBYzoTpZY3ZBGjt4znIBVj-YxUnyZ47BL9wNb3HV1jQpcutAxtP_j0faRnb-hbRdf-jEOLnUNqupruxpB8Fp0JSHeT8F17S64bEyIu_ndOvp42-9VLVr0_b1fLKjsBy1NWC-DO1VLxWkslmbRlUbu6lIXSyiIWtmGWFyAsU9YgTlfBKdtwBCi5Nfmc3P91T0P_M2JMh6OPDkMwHfZjPMCUEoJLLvJfSOhPcw</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>1864552625</pqid></control><display><type>article</type><title>Salient Region Detection Algorithm via KL Divergence and Multi-scale Merging</title><source>Alma/SFX Local Collection</source><creator>Luo, Huilan ; Wan, Chengtao ; Kong, Fansheng</creator><creatorcontrib>Luo, Huilan ; Wan, Chengtao ; Kong, Fansheng</creatorcontrib><description>A new salient region detection algorithm is proposed via KL divergence between color probability distributions of super-pixels and merging multi-scale saliency maps. Firstly, multi-scale super-pixel segmentations of an input image are computed. In each segmentation scale, an undirected close-loop connected graph is constructed, in which nodes are the super-pixels and the adjacent regions are expanded reasonably relying on the total number of super-pixels. Then, all the color values in each super-pixel are clustered in terms of their discriminative power to get the statistical probability distribution of the cluster labels for each super-pixel. Next, the edges between all adjacent super-pixel pairs are weighted with the harmonic-mean of KL divergence of their probability distributions, and then the multi-scale saliency maps are calculated according to boundary connectivity and region contrast. The final saliency map is obtained by calculating and optimizing the mean map of all the saliency maps with different</description><identifier>ISSN: 1009-5896</identifier><identifier>DOI: 10.11999/JEIT151145</identifier><language>chi</language><subject>Algorithms ; Color ; Divergence ; Electronics ; Image segmentation ; Mathematical analysis ; Merging</subject><ispartof>Dian zi yu xin xi xue bao = Journal of electronics &amp; information technology, 2016-07, Vol.38 (7), p.1594-1601</ispartof><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>314,776,780,27901,27902</link.rule.ids></links><search><creatorcontrib>Luo, Huilan</creatorcontrib><creatorcontrib>Wan, Chengtao</creatorcontrib><creatorcontrib>Kong, Fansheng</creatorcontrib><title>Salient Region Detection Algorithm via KL Divergence and Multi-scale Merging</title><title>Dian zi yu xin xi xue bao = Journal of electronics &amp; information technology</title><description>A new salient region detection algorithm is proposed via KL divergence between color probability distributions of super-pixels and merging multi-scale saliency maps. Firstly, multi-scale super-pixel segmentations of an input image are computed. In each segmentation scale, an undirected close-loop connected graph is constructed, in which nodes are the super-pixels and the adjacent regions are expanded reasonably relying on the total number of super-pixels. Then, all the color values in each super-pixel are clustered in terms of their discriminative power to get the statistical probability distribution of the cluster labels for each super-pixel. Next, the edges between all adjacent super-pixel pairs are weighted with the harmonic-mean of KL divergence of their probability distributions, and then the multi-scale saliency maps are calculated according to boundary connectivity and region contrast. The final saliency map is obtained by calculating and optimizing the mean map of all the saliency maps with different</description><subject>Algorithms</subject><subject>Color</subject><subject>Divergence</subject><subject>Electronics</subject><subject>Image segmentation</subject><subject>Mathematical analysis</subject><subject>Merging</subject><issn>1009-5896</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2016</creationdate><recordtype>article</recordtype><recordid>eNotjrFOwzAURT2ARFU68QMeWQJ-TmzHY9UWKKRCgjJXtvMSLLlJiZ1-P6lgukc60tEl5A7YA4DW-vF1s92DACjEFZkBYzoTpZY3ZBGjt4znIBVj-YxUnyZ47BL9wNb3HV1jQpcutAxtP_j0faRnb-hbRdf-jEOLnUNqupruxpB8Fp0JSHeT8F17S64bEyIu_ndOvp42-9VLVr0_b1fLKjsBy1NWC-DO1VLxWkslmbRlUbu6lIXSyiIWtmGWFyAsU9YgTlfBKdtwBCi5Nfmc3P91T0P_M2JMh6OPDkMwHfZjPMCUEoJLLvJfSOhPcw</recordid><startdate>20160701</startdate><enddate>20160701</enddate><creator>Luo, Huilan</creator><creator>Wan, Chengtao</creator><creator>Kong, Fansheng</creator><scope>7SC</scope><scope>7SP</scope><scope>8FD</scope><scope>JQ2</scope><scope>L7M</scope><scope>L~C</scope><scope>L~D</scope></search><sort><creationdate>20160701</creationdate><title>Salient Region Detection Algorithm via KL Divergence and Multi-scale Merging</title><author>Luo, Huilan ; Wan, Chengtao ; Kong, Fansheng</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-p103t-d512ccd672d967606b84dcd864797bee4bf0b2415b07baee6701c7bf2e1182ba3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>chi</language><creationdate>2016</creationdate><topic>Algorithms</topic><topic>Color</topic><topic>Divergence</topic><topic>Electronics</topic><topic>Image segmentation</topic><topic>Mathematical analysis</topic><topic>Merging</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Luo, Huilan</creatorcontrib><creatorcontrib>Wan, Chengtao</creatorcontrib><creatorcontrib>Kong, Fansheng</creatorcontrib><collection>Computer and Information Systems Abstracts</collection><collection>Electronics &amp; Communications Abstracts</collection><collection>Technology Research Database</collection><collection>ProQuest Computer Science Collection</collection><collection>Advanced Technologies Database with Aerospace</collection><collection>Computer and Information Systems Abstracts – Academic</collection><collection>Computer and Information Systems Abstracts Professional</collection><jtitle>Dian zi yu xin xi xue bao = Journal of electronics &amp; information technology</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Luo, Huilan</au><au>Wan, Chengtao</au><au>Kong, Fansheng</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Salient Region Detection Algorithm via KL Divergence and Multi-scale Merging</atitle><jtitle>Dian zi yu xin xi xue bao = Journal of electronics &amp; information technology</jtitle><date>2016-07-01</date><risdate>2016</risdate><volume>38</volume><issue>7</issue><spage>1594</spage><epage>1601</epage><pages>1594-1601</pages><issn>1009-5896</issn><abstract>A new salient region detection algorithm is proposed via KL divergence between color probability distributions of super-pixels and merging multi-scale saliency maps. Firstly, multi-scale super-pixel segmentations of an input image are computed. In each segmentation scale, an undirected close-loop connected graph is constructed, in which nodes are the super-pixels and the adjacent regions are expanded reasonably relying on the total number of super-pixels. Then, all the color values in each super-pixel are clustered in terms of their discriminative power to get the statistical probability distribution of the cluster labels for each super-pixel. Next, the edges between all adjacent super-pixel pairs are weighted with the harmonic-mean of KL divergence of their probability distributions, and then the multi-scale saliency maps are calculated according to boundary connectivity and region contrast. The final saliency map is obtained by calculating and optimizing the mean map of all the saliency maps with different</abstract><doi>10.11999/JEIT151145</doi><tpages>8</tpages></addata></record>
fulltext fulltext
identifier ISSN: 1009-5896
ispartof Dian zi yu xin xi xue bao = Journal of electronics & information technology, 2016-07, Vol.38 (7), p.1594-1601
issn 1009-5896
language chi
recordid cdi_proquest_miscellaneous_1864552625
source Alma/SFX Local Collection
subjects Algorithms
Color
Divergence
Electronics
Image segmentation
Mathematical analysis
Merging
title Salient Region Detection Algorithm via KL Divergence and Multi-scale Merging
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-02-20T13%3A22%3A21IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Salient%20Region%20Detection%20Algorithm%20via%20KL%20Divergence%20and%20Multi-scale%20Merging&rft.jtitle=Dian%20zi%20yu%20xin%20xi%20xue%20bao%20=%20Journal%20of%20electronics%20&%20information%20technology&rft.au=Luo,%20Huilan&rft.date=2016-07-01&rft.volume=38&rft.issue=7&rft.spage=1594&rft.epage=1601&rft.pages=1594-1601&rft.issn=1009-5896&rft_id=info:doi/10.11999/JEIT151145&rft_dat=%3Cproquest%3E1864552625%3C/proquest%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=1864552625&rft_id=info:pmid/&rfr_iscdi=true