A fast method for training support vector machines with a very large set of linear features

Current systems for object detection often use support vector machines (SVM) as the basic classification algorithm. A rather common case is to compute a small set of linear features and then train the classifier on these features. We present a fast method to train and evaluate SVM with many linear f...

Full description

Saved in:
Bibliographic Details
Main Authors: Maydt, J., Lienhart, R.
Format: Conference Proceeding
Language:English
Subjects:
Classification algorithms
Face detection
Fourier transforms
Kernel
Object detection
Principal component analysis
Runtime
Support vector machine classification
Support vector machines
Wavelet domain
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
cited_by
cites
container_end_page 312 vol.1
container_issue
container_start_page 309
container_title
container_volume 1
creator Maydt, J.
Lienhart, R.
description Current systems for object detection often use support vector machines (SVM) as the basic classification algorithm. A rather common case is to compute a small set of linear features and then train the classifier on these features. We present a fast method to train and evaluate SVM with many linear features and show results for face detection using a set of 210400 features. The resulting classifier is both more accurate and faster than a classifier trained on raw pixel features, which total up only to 576 features in our case.
doi_str_mv 10.1109/ICME.2002.1035780
format conference_proceeding
fullrecord <record><control><sourceid>ieee_6IE</sourceid><recordid>TN_cdi_ieee_primary_1035780</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>1035780</ieee_id><sourcerecordid>1035780</sourcerecordid><originalsourceid>FETCH-LOGICAL-i175t-5e47fb78180b97190d745b7e136fb5d0833f65dee64617372df2672ad53e451f3</originalsourceid><addsrcrecordid>eNotkM9KAzEYxAMiKHUfQLx8L7Brskk2u8eyVC20eNGTh5JtvnQj-48kVfr2BuwwMPAbmMMQ8showRhtnrftflOUlJYFo1yqmt6QrEmRzBWnQtyRLIRvmsQbKWt6T77WYHWIMGLsZwN29hC9dpObThDOyzL7CD94jImP-ti7CQP8utiDTthfYND-hBAwwmxhSLX2YFHHs8fwQG6tHgJm11yRz5fNR_uW795ft-16lzumZMwlCmU7VbOado1iDTVKyE4h45XtpKE157aSBrESFVNclcaWlSq1kRyFZJavyNP_rkPEw-LdqP3lcL2A_wG4MVFg</addsrcrecordid><sourcetype>Publisher</sourcetype><iscdi>true</iscdi><recordtype>conference_proceeding</recordtype></control><display><type>conference_proceeding</type><title>A fast method for training support vector machines with a very large set of linear features</title><source>IEEE Electronic Library (IEL) Conference Proceedings</source><creator>Maydt, J. ; Lienhart, R.</creator><creatorcontrib>Maydt, J. ; Lienhart, R.</creatorcontrib><description>Current systems for object detection often use support vector machines (SVM) as the basic classification algorithm. A rather common case is to compute a small set of linear features and then train the classifier on these features. We present a fast method to train and evaluate SVM with many linear features and show results for face detection using a set of 210400 features. The resulting classifier is both more accurate and faster than a classifier trained on raw pixel features, which total up only to 576 features in our case.</description><identifier>ISBN: 9780780373044</identifier><identifier>ISBN: 0780373049</identifier><identifier>DOI: 10.1109/ICME.2002.1035780</identifier><language>eng</language><publisher>IEEE</publisher><subject>Classification algorithms ; Face detection ; Fourier transforms ; Kernel ; Object detection ; Principal component analysis ; Runtime ; Support vector machine classification ; Support vector machines ; Wavelet domain</subject><ispartof>Proceedings. IEEE International Conference on Multimedia and Expo, 2002, Vol.1, p.309-312 vol.1</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/1035780$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>309,310,776,780,785,786,2051,4035,4036,27904,54899</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/1035780$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc></links><search><creatorcontrib>Maydt, J.</creatorcontrib><creatorcontrib>Lienhart, R.</creatorcontrib><title>A fast method for training support vector machines with a very large set of linear features</title><title>Proceedings. IEEE International Conference on Multimedia and Expo</title><addtitle>ICME</addtitle><description>Current systems for object detection often use support vector machines (SVM) as the basic classification algorithm. A rather common case is to compute a small set of linear features and then train the classifier on these features. We present a fast method to train and evaluate SVM with many linear features and show results for face detection using a set of 210400 features. The resulting classifier is both more accurate and faster than a classifier trained on raw pixel features, which total up only to 576 features in our case.</description><subject>Classification algorithms</subject><subject>Face detection</subject><subject>Fourier transforms</subject><subject>Kernel</subject><subject>Object detection</subject><subject>Principal component analysis</subject><subject>Runtime</subject><subject>Support vector machine classification</subject><subject>Support vector machines</subject><subject>Wavelet domain</subject><isbn>9780780373044</isbn><isbn>0780373049</isbn><fulltext>true</fulltext><rsrctype>conference_proceeding</rsrctype><creationdate>2002</creationdate><recordtype>conference_proceeding</recordtype><sourceid>6IE</sourceid><recordid>eNotkM9KAzEYxAMiKHUfQLx8L7Brskk2u8eyVC20eNGTh5JtvnQj-48kVfr2BuwwMPAbmMMQ8showRhtnrftflOUlJYFo1yqmt6QrEmRzBWnQtyRLIRvmsQbKWt6T77WYHWIMGLsZwN29hC9dpObThDOyzL7CD94jImP-ti7CQP8utiDTthfYND-hBAwwmxhSLX2YFHHs8fwQG6tHgJm11yRz5fNR_uW795ft-16lzumZMwlCmU7VbOado1iDTVKyE4h45XtpKE157aSBrESFVNclcaWlSq1kRyFZJavyNP_rkPEw-LdqP3lcL2A_wG4MVFg</recordid><startdate>2002</startdate><enddate>2002</enddate><creator>Maydt, J.</creator><creator>Lienhart, R.</creator><general>IEEE</general><scope>6IE</scope><scope>6IL</scope><scope>CBEJK</scope><scope>RIE</scope><scope>RIL</scope></search><sort><creationdate>2002</creationdate><title>A fast method for training support vector machines with a very large set of linear features</title><author>Maydt, J. ; Lienhart, R.</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-i175t-5e47fb78180b97190d745b7e136fb5d0833f65dee64617372df2672ad53e451f3</frbrgroupid><rsrctype>conference_proceedings</rsrctype><prefilter>conference_proceedings</prefilter><language>eng</language><creationdate>2002</creationdate><topic>Classification algorithms</topic><topic>Face detection</topic><topic>Fourier transforms</topic><topic>Kernel</topic><topic>Object detection</topic><topic>Principal component analysis</topic><topic>Runtime</topic><topic>Support vector machine classification</topic><topic>Support vector machines</topic><topic>Wavelet domain</topic><toplevel>online_resources</toplevel><creatorcontrib>Maydt, J.</creatorcontrib><creatorcontrib>Lienhart, R.</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 Xplore</collection><collection>IEEE Proceedings Order Plans (POP All) 1998-Present</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Maydt, J.</au><au>Lienhart, R.</au><format>book</format><genre>proceeding</genre><ristype>CONF</ristype><atitle>A fast method for training support vector machines with a very large set of linear features</atitle><btitle>Proceedings. IEEE International Conference on Multimedia and Expo</btitle><stitle>ICME</stitle><date>2002</date><risdate>2002</risdate><volume>1</volume><spage>309</spage><epage>312 vol.1</epage><pages>309-312 vol.1</pages><isbn>9780780373044</isbn><isbn>0780373049</isbn><abstract>Current systems for object detection often use support vector machines (SVM) as the basic classification algorithm. A rather common case is to compute a small set of linear features and then train the classifier on these features. We present a fast method to train and evaluate SVM with many linear features and show results for face detection using a set of 210400 features. The resulting classifier is both more accurate and faster than a classifier trained on raw pixel features, which total up only to 576 features in our case.</abstract><pub>IEEE</pub><doi>10.1109/ICME.2002.1035780</doi></addata></record>
fulltext fulltext_linktorsrc
identifier ISBN: 9780780373044
ispartof Proceedings. IEEE International Conference on Multimedia and Expo, 2002, Vol.1, p.309-312 vol.1
issn
language eng
recordid cdi_ieee_primary_1035780
source IEEE Electronic Library (IEL) Conference Proceedings
subjects Classification algorithms
Face detection
Fourier transforms
Kernel
Object detection
Principal component analysis
Runtime
Support vector machine classification
Support vector machines
Wavelet domain
title A fast method for training support vector machines with a very large set of linear features
url http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-21T13%3A42%3A10IST&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=A%20fast%20method%20for%20training%20support%20vector%20machines%20with%20a%20very%20large%20set%20of%20linear%20features&rft.btitle=Proceedings.%20IEEE%20International%20Conference%20on%20Multimedia%20and%20Expo&rft.au=Maydt,%20J.&rft.date=2002&rft.volume=1&rft.spage=309&rft.epage=312%20vol.1&rft.pages=309-312%20vol.1&rft.isbn=9780780373044&rft.isbn_list=0780373049&rft_id=info:doi/10.1109/ICME.2002.1035780&rft_dat=%3Cieee_6IE%3E1035780%3C/ieee_6IE%3E%3Cgrp_id%3Ecdi_FETCH-LOGICAL-i175t-5e47fb78180b97190d745b7e136fb5d0833f65dee64617372df2672ad53e451f3%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=1035780&rfr_iscdi=true