Loading…

"RegionCut" - Interactive multi-label segmentation utilizing cellular automaton

This paper addresses the problem of interactive image segmentation. We propose an extension of the GrowCut framework which follows Cellular Automaton theory and is comparable to a label propagation algorithm. Therefore, user labels are propagated according to Cellular Automaton until convergency. A...

Full description

Saved in:
Bibliographic Details
Main Authors: Arndt, O. J., Scheuermann, B., Rosenhahn, B.
Format: Conference Proceeding
Language:English
Subjects:
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
cited_by
cites
container_end_page 316
container_issue
container_start_page 309
container_title
container_volume
creator Arndt, O. J.
Scheuermann, B.
Rosenhahn, B.
description This paper addresses the problem of interactive image segmentation. We propose an extension of the GrowCut framework which follows Cellular Automaton theory and is comparable to a label propagation algorithm. Therefore, user labels are propagated according to Cellular Automaton until convergency. A common problem of GrowCut is the time consuming user initialization which requires distributed seeds. Our main contribution focuses on determining such an initialization utilizing GMMs and spherical coordinates. Furthermore we propose a new weight function based on the mean image gradient. According to our evaluation, our extensions result in a simplified user interaction and in better results in terms of accuracy and running time. Our experiments show that our method can compete with state-of-the-art energy minimization frameworks.
doi_str_mv 10.1109/WACV.2013.6475034
format conference_proceeding
fullrecord <record><control><sourceid>proquest_CHZPO</sourceid><recordid>TN_cdi_proquest_miscellaneous_1786218134</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>6475034</ieee_id><sourcerecordid>1786218134</sourcerecordid><originalsourceid>FETCH-LOGICAL-i208t-bf7ad0c9a8fbe8178401dbb56bf7c7943fd547ae3bef21a99bb9c32fa38464253</originalsourceid><addsrcrecordid>eNpVkMlqwzAURdUJGtJ8QOlGZNWNUo2WtAymQyAQKB2WRnKeg4psp7ZcaL--Lsmmq7e4h8O9D6FrRheMUXv3vszfFpwyscikVlTIEzSz2jCZaaGokvYUTXgmObHCsLN_meDnaMKUokRpSy_RrO8_KKVslGRWTtBm_gy70Db5kOaY4FWToHNlCl-A6yGmQKLzEHEPuxqa5NKI4iGFGH5Cs8MlxDhE12E3pLZ2qW2u0EXlYg-z452i14f7l_yJrDePq3y5JoFTk4ivtNvS0jpTeTBMG0nZ1nuVjUGprRTVVkntQHioOHPWem9LwSsnjByHKjFFtwfvvms_B-hTUYf-r45roB36YlRmnBkm5IjeHNAAAMW-C7XrvovjJ8UvTW5jEA</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>conference_proceeding</recordtype><pqid>1786218134</pqid></control><display><type>conference_proceeding</type><title>"RegionCut" - Interactive multi-label segmentation utilizing cellular automaton</title><source>IEEE Xplore All Conference Series</source><creator>Arndt, O. J. ; Scheuermann, B. ; Rosenhahn, B.</creator><creatorcontrib>Arndt, O. J. ; Scheuermann, B. ; Rosenhahn, B.</creatorcontrib><description>This paper addresses the problem of interactive image segmentation. We propose an extension of the GrowCut framework which follows Cellular Automaton theory and is comparable to a label propagation algorithm. Therefore, user labels are propagated according to Cellular Automaton until convergency. A common problem of GrowCut is the time consuming user initialization which requires distributed seeds. Our main contribution focuses on determining such an initialization utilizing GMMs and spherical coordinates. Furthermore we propose a new weight function based on the mean image gradient. According to our evaluation, our extensions result in a simplified user interaction and in better results in terms of accuracy and running time. Our experiments show that our method can compete with state-of-the-art energy minimization frameworks.</description><identifier>ISSN: 1550-5790</identifier><identifier>ISBN: 9781467350532</identifier><identifier>ISBN: 1467350532</identifier><identifier>EISSN: 2642-9381</identifier><identifier>EISSN: 1550-5790</identifier><identifier>EISBN: 9781467350549</identifier><identifier>EISBN: 1467350524</identifier><identifier>EISBN: 9781467350525</identifier><identifier>EISBN: 1467350540</identifier><identifier>DOI: 10.1109/WACV.2013.6475034</identifier><language>eng</language><publisher>IEEE</publisher><subject>Algorithm design and analysis ; Algorithms ; Automata ; Cellular automata ; Computer vision ; Consumption ; Equations ; Image color analysis ; Image edge detection ; Image segmentation ; Interactive ; Labels ; Segmentation ; Smoothing methods ; Workshops</subject><ispartof>2013 IEEE Workshop on Applications of Computer Vision (WACV), 2013, p.309-316</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/6475034$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>309,310,314,780,784,789,790,2058,27924,27925,54555,54920,54932</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/6475034$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc></links><search><creatorcontrib>Arndt, O. J.</creatorcontrib><creatorcontrib>Scheuermann, B.</creatorcontrib><creatorcontrib>Rosenhahn, B.</creatorcontrib><title>"RegionCut" - Interactive multi-label segmentation utilizing cellular automaton</title><title>2013 IEEE Workshop on Applications of Computer Vision (WACV)</title><addtitle>WACV</addtitle><description>This paper addresses the problem of interactive image segmentation. We propose an extension of the GrowCut framework which follows Cellular Automaton theory and is comparable to a label propagation algorithm. Therefore, user labels are propagated according to Cellular Automaton until convergency. A common problem of GrowCut is the time consuming user initialization which requires distributed seeds. Our main contribution focuses on determining such an initialization utilizing GMMs and spherical coordinates. Furthermore we propose a new weight function based on the mean image gradient. According to our evaluation, our extensions result in a simplified user interaction and in better results in terms of accuracy and running time. Our experiments show that our method can compete with state-of-the-art energy minimization frameworks.</description><subject>Algorithm design and analysis</subject><subject>Algorithms</subject><subject>Automata</subject><subject>Cellular automata</subject><subject>Computer vision</subject><subject>Consumption</subject><subject>Equations</subject><subject>Image color analysis</subject><subject>Image edge detection</subject><subject>Image segmentation</subject><subject>Interactive</subject><subject>Labels</subject><subject>Segmentation</subject><subject>Smoothing methods</subject><subject>Workshops</subject><issn>1550-5790</issn><issn>2642-9381</issn><issn>1550-5790</issn><isbn>9781467350532</isbn><isbn>1467350532</isbn><isbn>9781467350549</isbn><isbn>1467350524</isbn><isbn>9781467350525</isbn><isbn>1467350540</isbn><fulltext>true</fulltext><rsrctype>conference_proceeding</rsrctype><creationdate>2013</creationdate><recordtype>conference_proceeding</recordtype><sourceid>6IE</sourceid><recordid>eNpVkMlqwzAURdUJGtJ8QOlGZNWNUo2WtAymQyAQKB2WRnKeg4psp7ZcaL--Lsmmq7e4h8O9D6FrRheMUXv3vszfFpwyscikVlTIEzSz2jCZaaGokvYUTXgmObHCsLN_meDnaMKUokRpSy_RrO8_KKVslGRWTtBm_gy70Db5kOaY4FWToHNlCl-A6yGmQKLzEHEPuxqa5NKI4iGFGH5Cs8MlxDhE12E3pLZ2qW2u0EXlYg-z452i14f7l_yJrDePq3y5JoFTk4ivtNvS0jpTeTBMG0nZ1nuVjUGprRTVVkntQHioOHPWem9LwSsnjByHKjFFtwfvvms_B-hTUYf-r45roB36YlRmnBkm5IjeHNAAAMW-C7XrvovjJ8UvTW5jEA</recordid><startdate>201301</startdate><enddate>201301</enddate><creator>Arndt, O. J.</creator><creator>Scheuermann, B.</creator><creator>Rosenhahn, B.</creator><general>IEEE</general><scope>6IE</scope><scope>6IL</scope><scope>CBEJK</scope><scope>RIE</scope><scope>RIL</scope><scope>7SC</scope><scope>8FD</scope><scope>JQ2</scope><scope>L7M</scope><scope>L~C</scope><scope>L~D</scope></search><sort><creationdate>201301</creationdate><title>"RegionCut" - Interactive multi-label segmentation utilizing cellular automaton</title><author>Arndt, O. J. ; Scheuermann, B. ; Rosenhahn, B.</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-i208t-bf7ad0c9a8fbe8178401dbb56bf7c7943fd547ae3bef21a99bb9c32fa38464253</frbrgroupid><rsrctype>conference_proceedings</rsrctype><prefilter>conference_proceedings</prefilter><language>eng</language><creationdate>2013</creationdate><topic>Algorithm design and analysis</topic><topic>Algorithms</topic><topic>Automata</topic><topic>Cellular automata</topic><topic>Computer vision</topic><topic>Consumption</topic><topic>Equations</topic><topic>Image color analysis</topic><topic>Image edge detection</topic><topic>Image segmentation</topic><topic>Interactive</topic><topic>Labels</topic><topic>Segmentation</topic><topic>Smoothing methods</topic><topic>Workshops</topic><toplevel>online_resources</toplevel><creatorcontrib>Arndt, O. J.</creatorcontrib><creatorcontrib>Scheuermann, B.</creatorcontrib><creatorcontrib>Rosenhahn, B.</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 Online</collection><collection>IEEE Proceedings Order Plans (POP All) 1998-Present</collection><collection>Computer and Information Systems 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></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Arndt, O. J.</au><au>Scheuermann, B.</au><au>Rosenhahn, B.</au><format>book</format><genre>proceeding</genre><ristype>CONF</ristype><atitle>"RegionCut" - Interactive multi-label segmentation utilizing cellular automaton</atitle><btitle>2013 IEEE Workshop on Applications of Computer Vision (WACV)</btitle><stitle>WACV</stitle><date>2013-01</date><risdate>2013</risdate><spage>309</spage><epage>316</epage><pages>309-316</pages><issn>1550-5790</issn><eissn>2642-9381</eissn><eissn>1550-5790</eissn><isbn>9781467350532</isbn><isbn>1467350532</isbn><eisbn>9781467350549</eisbn><eisbn>1467350524</eisbn><eisbn>9781467350525</eisbn><eisbn>1467350540</eisbn><abstract>This paper addresses the problem of interactive image segmentation. We propose an extension of the GrowCut framework which follows Cellular Automaton theory and is comparable to a label propagation algorithm. Therefore, user labels are propagated according to Cellular Automaton until convergency. A common problem of GrowCut is the time consuming user initialization which requires distributed seeds. Our main contribution focuses on determining such an initialization utilizing GMMs and spherical coordinates. Furthermore we propose a new weight function based on the mean image gradient. According to our evaluation, our extensions result in a simplified user interaction and in better results in terms of accuracy and running time. Our experiments show that our method can compete with state-of-the-art energy minimization frameworks.</abstract><pub>IEEE</pub><doi>10.1109/WACV.2013.6475034</doi><tpages>8</tpages></addata></record>
fulltext fulltext_linktorsrc
identifier ISSN: 1550-5790
ispartof 2013 IEEE Workshop on Applications of Computer Vision (WACV), 2013, p.309-316
issn 1550-5790
2642-9381
1550-5790
language eng
recordid cdi_proquest_miscellaneous_1786218134
source IEEE Xplore All Conference Series
subjects Algorithm design and analysis
Algorithms
Automata
Cellular automata
Computer vision
Consumption
Equations
Image color analysis
Image edge detection
Image segmentation
Interactive
Labels
Segmentation
Smoothing methods
Workshops
title "RegionCut" - Interactive multi-label segmentation utilizing cellular automaton
url http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-24T21%3A25%3A18IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_CHZPO&rft_val_fmt=info:ofi/fmt:kev:mtx:book&rft.genre=proceeding&rft.atitle=%22RegionCut%22%20-%20Interactive%20multi-label%20segmentation%20utilizing%20cellular%20automaton&rft.btitle=2013%20IEEE%20Workshop%20on%20Applications%20of%20Computer%20Vision%20(WACV)&rft.au=Arndt,%20O.%20J.&rft.date=2013-01&rft.spage=309&rft.epage=316&rft.pages=309-316&rft.issn=1550-5790&rft.eissn=2642-9381&rft.isbn=9781467350532&rft.isbn_list=1467350532&rft_id=info:doi/10.1109/WACV.2013.6475034&rft.eisbn=9781467350549&rft.eisbn_list=1467350524&rft.eisbn_list=9781467350525&rft.eisbn_list=1467350540&rft_dat=%3Cproquest_CHZPO%3E1786218134%3C/proquest_CHZPO%3E%3Cgrp_id%3Ecdi_FETCH-LOGICAL-i208t-bf7ad0c9a8fbe8178401dbb56bf7c7943fd547ae3bef21a99bb9c32fa38464253%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_pqid=1786218134&rft_id=info:pmid/&rft_ieee_id=6475034&rfr_iscdi=true