Loading…
Supervised multispectral image segmentation with power watersheds
In recent years, graph-based methods have had a significant impact on image segmentation. They are especially noteworthy for supervised segmentation, where the user provides task-specific foreground and background seeds. We adapt the power watershed framework to multispectral and hyperspectral image...
Saved in:
| Main Authors: | , |
|---|---|
| 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 | 1588 |
| container_issue | |
| container_start_page | 1585 |
| container_title | |
| container_volume | |
| creator | Jordan, J. Angelopoulou, E. |
| description | In recent years, graph-based methods have had a significant impact on image segmentation. They are especially noteworthy for supervised segmentation, where the user provides task-specific foreground and background seeds. We adapt the power watershed framework to multispectral and hyperspectral image data and incorporate similarity measures from the field of spectral matching. We also propose a new data-driven graph edge weighting. Our weights are computed by the topological information of a self-organizing map. We show that graph weights based on a simple Lp-norm, as used in other modalities, do not give satisfactory segmentation results for multispectral data, while similarity measures that were specifically designed for this domain perform better. Our new approach is competitive and has an advantage in some of the tested scenarios. |
| doi_str_mv | 10.1109/ICIP.2012.6467177 |
| format | conference_proceeding |
| fullrecord | <record><control><sourceid>ieee_6IE</sourceid><recordid>TN_cdi_ieee_primary_6467177</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>6467177</ieee_id><sourcerecordid>6467177</sourcerecordid><originalsourceid>FETCH-LOGICAL-i175t-149f0aeb7c43095fbeee34a8d4ddae77af594fb876994656d9408d99e12d2bb03</originalsourceid><addsrcrecordid>eNo1kNtKw0AYhNcTmNY-gHiTF0jcfw_Z3csSrAYKCup12XT_tCtJG7Jbg29vwHo1DMN8DEPIPdAcgJrHqqzeckaB5YUoFCh1QRZGaZgMZ5JzdkkSxjVkWgpzRWb_gYBrkoBkLBNa01syC-GL0gnEISHL91OPw7cP6NLu1EYfetzGwbap7-wO04C7Dg_RRn88pKOP-7Q_jjiko404hD26cEduGtsGXJx1Tj5XTx_lS7Z-fa7K5TrzoGTMQJiGWqzVVnBqZFMjIhdWO-GcRaVsI41oaq0KY0QhC2cE1c4YBOZYXVM-Jw9_XD81N_0w7Rt-Nucr-C-g6E-C</addsrcrecordid><sourcetype>Publisher</sourcetype><iscdi>true</iscdi><recordtype>conference_proceeding</recordtype></control><display><type>conference_proceeding</type><title>Supervised multispectral image segmentation with power watersheds</title><source>IEEE Electronic Library (IEL) Conference Proceedings</source><creator>Jordan, J. ; Angelopoulou, E.</creator><creatorcontrib>Jordan, J. ; Angelopoulou, E.</creatorcontrib><description>In recent years, graph-based methods have had a significant impact on image segmentation. They are especially noteworthy for supervised segmentation, where the user provides task-specific foreground and background seeds. We adapt the power watershed framework to multispectral and hyperspectral image data and incorporate similarity measures from the field of spectral matching. We also propose a new data-driven graph edge weighting. Our weights are computed by the topological information of a self-organizing map. We show that graph weights based on a simple Lp-norm, as used in other modalities, do not give satisfactory segmentation results for multispectral data, while similarity measures that were specifically designed for this domain perform better. Our new approach is competitive and has an advantage in some of the tested scenarios.</description><identifier>ISSN: 1522-4880</identifier><identifier>ISBN: 1467325341</identifier><identifier>ISBN: 9781467325349</identifier><identifier>EISSN: 2381-8549</identifier><identifier>EISBN: 9781467325332</identifier><identifier>EISBN: 1467325325</identifier><identifier>EISBN: 9781467325325</identifier><identifier>EISBN: 1467325333</identifier><identifier>DOI: 10.1109/ICIP.2012.6467177</identifier><language>eng</language><publisher>IEEE</publisher><subject>Algorithm design and analysis ; Clustering algorithms ; Distance Learning ; Distance measurement ; Hyperspectral imaging ; Image edge detection ; Image segmentation ; Lattices ; Multispectral imaging ; Self organizing feature maps ; Vectors</subject><ispartof>2012 19th IEEE International Conference on Image Processing, 2012, p.1585-1588</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/6467177$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>309,310,780,784,789,790,2058,27925,54555,54920,54932</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/6467177$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc></links><search><creatorcontrib>Jordan, J.</creatorcontrib><creatorcontrib>Angelopoulou, E.</creatorcontrib><title>Supervised multispectral image segmentation with power watersheds</title><title>2012 19th IEEE International Conference on Image Processing</title><addtitle>ICIP</addtitle><description>In recent years, graph-based methods have had a significant impact on image segmentation. They are especially noteworthy for supervised segmentation, where the user provides task-specific foreground and background seeds. We adapt the power watershed framework to multispectral and hyperspectral image data and incorporate similarity measures from the field of spectral matching. We also propose a new data-driven graph edge weighting. Our weights are computed by the topological information of a self-organizing map. We show that graph weights based on a simple Lp-norm, as used in other modalities, do not give satisfactory segmentation results for multispectral data, while similarity measures that were specifically designed for this domain perform better. Our new approach is competitive and has an advantage in some of the tested scenarios.</description><subject>Algorithm design and analysis</subject><subject>Clustering algorithms</subject><subject>Distance Learning</subject><subject>Distance measurement</subject><subject>Hyperspectral imaging</subject><subject>Image edge detection</subject><subject>Image segmentation</subject><subject>Lattices</subject><subject>Multispectral imaging</subject><subject>Self organizing feature maps</subject><subject>Vectors</subject><issn>1522-4880</issn><issn>2381-8549</issn><isbn>1467325341</isbn><isbn>9781467325349</isbn><isbn>9781467325332</isbn><isbn>1467325325</isbn><isbn>9781467325325</isbn><isbn>1467325333</isbn><fulltext>true</fulltext><rsrctype>conference_proceeding</rsrctype><creationdate>2012</creationdate><recordtype>conference_proceeding</recordtype><sourceid>6IE</sourceid><recordid>eNo1kNtKw0AYhNcTmNY-gHiTF0jcfw_Z3csSrAYKCup12XT_tCtJG7Jbg29vwHo1DMN8DEPIPdAcgJrHqqzeckaB5YUoFCh1QRZGaZgMZ5JzdkkSxjVkWgpzRWb_gYBrkoBkLBNa01syC-GL0gnEISHL91OPw7cP6NLu1EYfetzGwbap7-wO04C7Dg_RRn88pKOP-7Q_jjiko404hD26cEduGtsGXJx1Tj5XTx_lS7Z-fa7K5TrzoGTMQJiGWqzVVnBqZFMjIhdWO-GcRaVsI41oaq0KY0QhC2cE1c4YBOZYXVM-Jw9_XD81N_0w7Rt-Nucr-C-g6E-C</recordid><startdate>201209</startdate><enddate>201209</enddate><creator>Jordan, J.</creator><creator>Angelopoulou, E.</creator><general>IEEE</general><scope>6IE</scope><scope>6IH</scope><scope>CBEJK</scope><scope>RIE</scope><scope>RIO</scope></search><sort><creationdate>201209</creationdate><title>Supervised multispectral image segmentation with power watersheds</title><author>Jordan, J. ; Angelopoulou, E.</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-i175t-149f0aeb7c43095fbeee34a8d4ddae77af594fb876994656d9408d99e12d2bb03</frbrgroupid><rsrctype>conference_proceedings</rsrctype><prefilter>conference_proceedings</prefilter><language>eng</language><creationdate>2012</creationdate><topic>Algorithm design and analysis</topic><topic>Clustering algorithms</topic><topic>Distance Learning</topic><topic>Distance measurement</topic><topic>Hyperspectral imaging</topic><topic>Image edge detection</topic><topic>Image segmentation</topic><topic>Lattices</topic><topic>Multispectral imaging</topic><topic>Self organizing feature maps</topic><topic>Vectors</topic><toplevel>online_resources</toplevel><creatorcontrib>Jordan, J.</creatorcontrib><creatorcontrib>Angelopoulou, E.</creatorcontrib><collection>IEEE Electronic Library (IEL) Conference Proceedings</collection><collection>IEEE Proceedings Order Plan (POP) 1998-present by volume</collection><collection>IEEE Xplore All Conference Proceedings</collection><collection>IEEE Xplore</collection><collection>IEEE Proceedings Order Plans (POP) 1998-present</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Jordan, J.</au><au>Angelopoulou, E.</au><format>book</format><genre>proceeding</genre><ristype>CONF</ristype><atitle>Supervised multispectral image segmentation with power watersheds</atitle><btitle>2012 19th IEEE International Conference on Image Processing</btitle><stitle>ICIP</stitle><date>2012-09</date><risdate>2012</risdate><spage>1585</spage><epage>1588</epage><pages>1585-1588</pages><issn>1522-4880</issn><eissn>2381-8549</eissn><isbn>1467325341</isbn><isbn>9781467325349</isbn><eisbn>9781467325332</eisbn><eisbn>1467325325</eisbn><eisbn>9781467325325</eisbn><eisbn>1467325333</eisbn><abstract>In recent years, graph-based methods have had a significant impact on image segmentation. They are especially noteworthy for supervised segmentation, where the user provides task-specific foreground and background seeds. We adapt the power watershed framework to multispectral and hyperspectral image data and incorporate similarity measures from the field of spectral matching. We also propose a new data-driven graph edge weighting. Our weights are computed by the topological information of a self-organizing map. We show that graph weights based on a simple Lp-norm, as used in other modalities, do not give satisfactory segmentation results for multispectral data, while similarity measures that were specifically designed for this domain perform better. Our new approach is competitive and has an advantage in some of the tested scenarios.</abstract><pub>IEEE</pub><doi>10.1109/ICIP.2012.6467177</doi><tpages>4</tpages></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | ISSN: 1522-4880 |
| ispartof | 2012 19th IEEE International Conference on Image Processing, 2012, p.1585-1588 |
| issn | 1522-4880 2381-8549 |
| language | eng |
| recordid | cdi_ieee_primary_6467177 |
| source | IEEE Electronic Library (IEL) Conference Proceedings |
| subjects | Algorithm design and analysis Clustering algorithms Distance Learning Distance measurement Hyperspectral imaging Image edge detection Image segmentation Lattices Multispectral imaging Self organizing feature maps Vectors |
| title | Supervised multispectral image segmentation with power watersheds |
| url | http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-06T20%3A47%3A40IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-ieee_6IE&rft_val_fmt=info:ofi/fmt:kev:mtx:book&rft.genre=proceeding&rft.atitle=Supervised%20multispectral%20image%20segmentation%20with%20power%20watersheds&rft.btitle=2012%2019th%20IEEE%20International%20Conference%20on%20Image%20Processing&rft.au=Jordan,%20J.&rft.date=2012-09&rft.spage=1585&rft.epage=1588&rft.pages=1585-1588&rft.issn=1522-4880&rft.eissn=2381-8549&rft.isbn=1467325341&rft.isbn_list=9781467325349&rft_id=info:doi/10.1109/ICIP.2012.6467177&rft.eisbn=9781467325332&rft.eisbn_list=1467325325&rft.eisbn_list=9781467325325&rft.eisbn_list=1467325333&rft_dat=%3Cieee_6IE%3E6467177%3C/ieee_6IE%3E%3Cgrp_id%3Ecdi_FETCH-LOGICAL-i175t-149f0aeb7c43095fbeee34a8d4ddae77af594fb876994656d9408d99e12d2bb03%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_id=info:pmid/&rft_ieee_id=6467177&rfr_iscdi=true |