Object Detection with Pixel Intensity Comparisons Organized in Decision Trees
We describe a method for visual object detection based on an ensemble of optimized decision trees organized in a cascade of rejectors. The trees use pixel intensity comparisons in their internal nodes and this makes them able to process image regions very fast. Experimental analysis is provided thro...
Gespeichert in:
| Hauptverfasser: | , , , , |
|---|---|
| Format: | Artikel |
| 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 | Markuš, Nenad Frljak, Miroslav Pandžić, Igor S Ahlberg, Jörgen Forchheimer, Robert |
| description | We describe a method for visual object detection based on an ensemble of
optimized decision trees organized in a cascade of rejectors. The trees use
pixel intensity comparisons in their internal nodes and this makes them able to
process image regions very fast. Experimental analysis is provided through a
face detection problem. The obtained results are encouraging and demonstrate
that the method has practical value. Additionally, we analyse its sensitivity
to noise and show how to perform fast rotation invariant object detection.
Complete source code is provided at https://github.com/nenadmarkus/pico. |
| doi_str_mv | 10.48550/arxiv.1305.4537 |
| format | Article |
| fullrecord | <record><control><sourceid>arxiv_GOX</sourceid><recordid>TN_cdi_arxiv_primary_1305_4537</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>1305_4537</sourcerecordid><originalsourceid>FETCH-LOGICAL-a657-cc29b5084d426c2dd25066af4278299a7fa5add77c9a522c9f5a3e9712485a283</originalsourceid><addsrcrecordid>eNotzz1PwzAUhWEvDKiwMyH_gQTn2o7jEYWvSkVhyB7d2g4YtU5lW9Dy60mg05neIz2E3FSsFI2U7A7j0X-VFWeyFJKrS_LabT-dyfTB5Xn8FOi3zx_0zR_djq5DdiH5fKLttD9g9GkKiXbxHYP_cZb6MHfGpyXro3PpilyMuEvu-rwr0j899u1Lseme1-39psBaqsIY0FvJGmEF1AasBcnqGkcBqgGtUY0o0VqljEYJYPQokTutKpgRCA1fkdv_2z_OcIh-j_E0LKxhYfFf3IFH8Q</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>Object Detection with Pixel Intensity Comparisons Organized in Decision Trees</title><source>arXiv.org</source><creator>Markuš, Nenad ; Frljak, Miroslav ; Pandžić, Igor S ; Ahlberg, Jörgen ; Forchheimer, Robert</creator><creatorcontrib>Markuš, Nenad ; Frljak, Miroslav ; Pandžić, Igor S ; Ahlberg, Jörgen ; Forchheimer, Robert</creatorcontrib><description>We describe a method for visual object detection based on an ensemble of
optimized decision trees organized in a cascade of rejectors. The trees use
pixel intensity comparisons in their internal nodes and this makes them able to
process image regions very fast. Experimental analysis is provided through a
face detection problem. The obtained results are encouraging and demonstrate
that the method has practical value. Additionally, we analyse its sensitivity
to noise and show how to perform fast rotation invariant object detection.
Complete source code is provided at https://github.com/nenadmarkus/pico.</description><identifier>DOI: 10.48550/arxiv.1305.4537</identifier><language>eng</language><subject>Computer Science - Computer Vision and Pattern Recognition</subject><creationdate>2013-05</creationdate><rights>http://arxiv.org/licenses/nonexclusive-distrib/1.0</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>228,230,776,881</link.rule.ids><linktorsrc>$$Uhttps://arxiv.org/abs/1305.4537$$EView_record_in_Cornell_University$$FView_record_in_$$GCornell_University$$Hfree_for_read</linktorsrc><backlink>$$Uhttps://doi.org/10.48550/arXiv.1305.4537$$DView paper in arXiv$$Hfree_for_read</backlink></links><search><creatorcontrib>Markuš, Nenad</creatorcontrib><creatorcontrib>Frljak, Miroslav</creatorcontrib><creatorcontrib>Pandžić, Igor S</creatorcontrib><creatorcontrib>Ahlberg, Jörgen</creatorcontrib><creatorcontrib>Forchheimer, Robert</creatorcontrib><title>Object Detection with Pixel Intensity Comparisons Organized in Decision Trees</title><description>We describe a method for visual object detection based on an ensemble of
optimized decision trees organized in a cascade of rejectors. The trees use
pixel intensity comparisons in their internal nodes and this makes them able to
process image regions very fast. Experimental analysis is provided through a
face detection problem. The obtained results are encouraging and demonstrate
that the method has practical value. Additionally, we analyse its sensitivity
to noise and show how to perform fast rotation invariant object detection.
Complete source code is provided at https://github.com/nenadmarkus/pico.</description><subject>Computer Science - Computer Vision and Pattern Recognition</subject><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2013</creationdate><recordtype>article</recordtype><sourceid>GOX</sourceid><recordid>eNotzz1PwzAUhWEvDKiwMyH_gQTn2o7jEYWvSkVhyB7d2g4YtU5lW9Dy60mg05neIz2E3FSsFI2U7A7j0X-VFWeyFJKrS_LabT-dyfTB5Xn8FOi3zx_0zR_djq5DdiH5fKLttD9g9GkKiXbxHYP_cZb6MHfGpyXro3PpilyMuEvu-rwr0j899u1Lseme1-39psBaqsIY0FvJGmEF1AasBcnqGkcBqgGtUY0o0VqljEYJYPQokTutKpgRCA1fkdv_2z_OcIh-j_E0LKxhYfFf3IFH8Q</recordid><startdate>20130520</startdate><enddate>20130520</enddate><creator>Markuš, Nenad</creator><creator>Frljak, Miroslav</creator><creator>Pandžić, Igor S</creator><creator>Ahlberg, Jörgen</creator><creator>Forchheimer, Robert</creator><scope>AKY</scope><scope>GOX</scope></search><sort><creationdate>20130520</creationdate><title>Object Detection with Pixel Intensity Comparisons Organized in Decision Trees</title><author>Markuš, Nenad ; Frljak, Miroslav ; Pandžić, Igor S ; Ahlberg, Jörgen ; Forchheimer, Robert</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-a657-cc29b5084d426c2dd25066af4278299a7fa5add77c9a522c9f5a3e9712485a283</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2013</creationdate><topic>Computer Science - Computer Vision and Pattern Recognition</topic><toplevel>online_resources</toplevel><creatorcontrib>Markuš, Nenad</creatorcontrib><creatorcontrib>Frljak, Miroslav</creatorcontrib><creatorcontrib>Pandžić, Igor S</creatorcontrib><creatorcontrib>Ahlberg, Jörgen</creatorcontrib><creatorcontrib>Forchheimer, Robert</creatorcontrib><collection>arXiv Computer Science</collection><collection>arXiv.org</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Markuš, Nenad</au><au>Frljak, Miroslav</au><au>Pandžić, Igor S</au><au>Ahlberg, Jörgen</au><au>Forchheimer, Robert</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Object Detection with Pixel Intensity Comparisons Organized in Decision Trees</atitle><date>2013-05-20</date><risdate>2013</risdate><abstract>We describe a method for visual object detection based on an ensemble of
optimized decision trees organized in a cascade of rejectors. The trees use
pixel intensity comparisons in their internal nodes and this makes them able to
process image regions very fast. Experimental analysis is provided through a
face detection problem. The obtained results are encouraging and demonstrate
that the method has practical value. Additionally, we analyse its sensitivity
to noise and show how to perform fast rotation invariant object detection.
Complete source code is provided at https://github.com/nenadmarkus/pico.</abstract><doi>10.48550/arxiv.1305.4537</doi><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | DOI: 10.48550/arxiv.1305.4537 |
| ispartof | |
| issn | |
| language | eng |
| recordid | cdi_arxiv_primary_1305_4537 |
| source | arXiv.org |
| subjects | Computer Science - Computer Vision and Pattern Recognition |
| title | Object Detection with Pixel Intensity Comparisons Organized in Decision Trees |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-30T10%3A20%3A47IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-arxiv_GOX&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Object%20Detection%20with%20Pixel%20Intensity%20Comparisons%20Organized%20in%20Decision%20Trees&rft.au=Marku%C5%A1,%20Nenad&rft.date=2013-05-20&rft_id=info:doi/10.48550/arxiv.1305.4537&rft_dat=%3Carxiv_GOX%3E1305_4537%3C/arxiv_GOX%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 |