Performance Evaluation of Text Detection and Tracking in Video
Identifieur interne : 001028 ( Main/Exploration ); précédent : 001027; suivant : 001029Performance Evaluation of Text Detection and Tracking in Video
Auteurs : Vasant Manohar [États-Unis] ; Padmanabhan Soundararajan [États-Unis] ; Matthew Boonstra [États-Unis] ; Harish Raju [États-Unis] ; Dmitry Goldgof [États-Unis] ; Rangachar Kasturi [États-Unis] ; John Garofolo [États-Unis]Source :
- Lecture Notes in Computer Science [ 0302-9743 ] ; 2006.
Abstract
Abstract: Text detection and tracking is an important step in a video content analysis system as it brings important semantic clues which is a vital supplemental source of index information. While there has been a significant amount of research done on video text detection and tracking, there are very few works on performance evaluation of such systems. Evaluations of this nature have not been attempted because of the extensive effort required to establish a reliable ground truth even for a moderate video dataset. However, such ventures are gaining importance now. In this paper, we propose a generic method for evaluation of object detection and tracking systems in video domains where ground truth objects can be bounded by simple geometric shapes (polygons, ellipses). Two comprehensive measures, one each for detection and tracking, are proposed and substantiated to capture different aspects of the task in a single score. We choose text detection and tracking tasks to show the effectiveness of our evaluation framework. Results are presented from evaluations of existing algorithms using real world data and the metrics are shown to be effective in measuring the total accuracy of these detection and tracking algorithms.
Url:
DOI: 10.1007/11669487_51
Affiliations:
Links toward previous steps (curation, corpus...)
- to stream Istex, to step Corpus: 001451
- to stream Istex, to step Curation: 001365
- to stream Istex, to step Checkpoint: 000A01
- to stream Main, to step Merge: 001045
- to stream Main, to step Curation: 001028
Le document en format XML
<record><TEI wicri:istexFullTextTei="biblStruct"><teiHeader><fileDesc><titleStmt><title xml:lang="en">Performance Evaluation of Text Detection and Tracking in Video</title><author><name sortKey="Manohar, Vasant" sort="Manohar, Vasant" uniqKey="Manohar V" first="Vasant" last="Manohar">Vasant Manohar</name></author><author><name sortKey="Soundararajan, Padmanabhan" sort="Soundararajan, Padmanabhan" uniqKey="Soundararajan P" first="Padmanabhan" last="Soundararajan">Padmanabhan Soundararajan</name></author><author><name sortKey="Boonstra, Matthew" sort="Boonstra, Matthew" uniqKey="Boonstra M" first="Matthew" last="Boonstra">Matthew Boonstra</name></author><author><name sortKey="Raju, Harish" sort="Raju, Harish" uniqKey="Raju H" first="Harish" last="Raju">Harish Raju</name></author><author><name sortKey="Goldgof, Dmitry" sort="Goldgof, Dmitry" uniqKey="Goldgof D" first="Dmitry" last="Goldgof">Dmitry Goldgof</name></author><author><name sortKey="Kasturi, Rangachar" sort="Kasturi, Rangachar" uniqKey="Kasturi R" first="Rangachar" last="Kasturi">Rangachar Kasturi</name></author><author><name sortKey="Garofolo, John" sort="Garofolo, John" uniqKey="Garofolo J" first="John" last="Garofolo">John Garofolo</name></author></titleStmt><publicationStmt><idno type="wicri:source">ISTEX</idno><idno type="RBID">ISTEX:D6D2390262CD9AEA06063F8AF743A0799CC6A87A</idno><date when="2006" year="2006">2006</date><idno type="doi">10.1007/11669487_51</idno><idno type="url">https://api.istex.fr/document/D6D2390262CD9AEA06063F8AF743A0799CC6A87A/fulltext/pdf</idno><idno type="wicri:Area/Istex/Corpus">001451</idno><idno type="wicri:Area/Istex/Curation">001365</idno><idno type="wicri:Area/Istex/Checkpoint">000A01</idno><idno type="wicri:doubleKey">0302-9743:2006:Manohar V:performance:evaluation:of</idno><idno type="wicri:Area/Main/Merge">001045</idno><idno type="wicri:Area/Main/Curation">001028</idno><idno type="wicri:Area/Main/Exploration">001028</idno></publicationStmt><sourceDesc><biblStruct><analytic><title level="a" type="main" xml:lang="en">Performance Evaluation of Text Detection and Tracking in Video</title><author><name sortKey="Manohar, Vasant" sort="Manohar, Vasant" uniqKey="Manohar V" first="Vasant" last="Manohar">Vasant Manohar</name><affiliation wicri:level="2"><country xml:lang="fr">États-Unis</country><placeName><region type="state">Floride</region></placeName><wicri:cityArea>University of South Florida, Tampa</wicri:cityArea></affiliation><affiliation wicri:level="1"><country wicri:rule="url">États-Unis</country></affiliation></author><author><name sortKey="Soundararajan, Padmanabhan" sort="Soundararajan, Padmanabhan" uniqKey="Soundararajan P" first="Padmanabhan" last="Soundararajan">Padmanabhan Soundararajan</name><affiliation wicri:level="2"><country xml:lang="fr">États-Unis</country><placeName><region type="state">Floride</region></placeName><wicri:cityArea>University of South Florida, Tampa</wicri:cityArea></affiliation><affiliation wicri:level="1"><country wicri:rule="url">États-Unis</country></affiliation></author><author><name sortKey="Boonstra, Matthew" sort="Boonstra, Matthew" uniqKey="Boonstra M" first="Matthew" last="Boonstra">Matthew Boonstra</name><affiliation wicri:level="2"><country xml:lang="fr">États-Unis</country><placeName><region type="state">Floride</region></placeName><wicri:cityArea>University of South Florida, Tampa</wicri:cityArea></affiliation><affiliation wicri:level="1"><country wicri:rule="url">États-Unis</country></affiliation></author><author><name sortKey="Raju, Harish" sort="Raju, Harish" uniqKey="Raju H" first="Harish" last="Raju">Harish Raju</name><affiliation wicri:level="2"><country xml:lang="fr">États-Unis</country><placeName><region type="state">Pennsylvanie</region></placeName><wicri:cityArea>Advanced Interfaces Inc., State College</wicri:cityArea></affiliation><affiliation><wicri:noCountry code="no comma">E-mail: hraju@advancedinterfaces.com</wicri:noCountry></affiliation></author><author><name sortKey="Goldgof, Dmitry" sort="Goldgof, Dmitry" uniqKey="Goldgof D" first="Dmitry" last="Goldgof">Dmitry Goldgof</name><affiliation wicri:level="2"><country xml:lang="fr">États-Unis</country><placeName><region type="state">Floride</region></placeName><wicri:cityArea>University of South Florida, Tampa</wicri:cityArea></affiliation><affiliation wicri:level="1"><country wicri:rule="url">États-Unis</country></affiliation></author><author><name sortKey="Kasturi, Rangachar" sort="Kasturi, Rangachar" uniqKey="Kasturi R" first="Rangachar" last="Kasturi">Rangachar Kasturi</name><affiliation wicri:level="2"><country xml:lang="fr">États-Unis</country><placeName><region type="state">Floride</region></placeName><wicri:cityArea>University of South Florida, Tampa</wicri:cityArea></affiliation><affiliation wicri:level="1"><country wicri:rule="url">États-Unis</country></affiliation></author><author><name sortKey="Garofolo, John" sort="Garofolo, John" uniqKey="Garofolo J" first="John" last="Garofolo">John Garofolo</name><affiliation wicri:level="2"><country xml:lang="fr">États-Unis</country><placeName><region type="state">Maryland</region></placeName><wicri:cityArea>National Institute of Standards and Technology, Gaithersburg</wicri:cityArea></affiliation><affiliation><wicri:noCountry code="no comma">E-mail: john.garofolo@nist.gov</wicri:noCountry></affiliation></author></analytic><monogr></monogr><series><title level="s">Lecture Notes in Computer Science</title><imprint><date>2006</date></imprint><idno type="ISSN">0302-9743</idno><idno type="eISSN">1611-3349</idno><idno type="ISSN">0302-9743</idno></series><idno type="istex">D6D2390262CD9AEA06063F8AF743A0799CC6A87A</idno><idno type="DOI">10.1007/11669487_51</idno><idno type="ChapterID">51</idno><idno type="ChapterID">Chap51</idno></biblStruct></sourceDesc><seriesStmt><idno type="ISSN">0302-9743</idno></seriesStmt></fileDesc><profileDesc><textClass></textClass><langUsage><language ident="en">en</language></langUsage></profileDesc></teiHeader><front><div type="abstract" xml:lang="en">Abstract: Text detection and tracking is an important step in a video content analysis system as it brings important semantic clues which is a vital supplemental source of index information. While there has been a significant amount of research done on video text detection and tracking, there are very few works on performance evaluation of such systems. Evaluations of this nature have not been attempted because of the extensive effort required to establish a reliable ground truth even for a moderate video dataset. However, such ventures are gaining importance now. In this paper, we propose a generic method for evaluation of object detection and tracking systems in video domains where ground truth objects can be bounded by simple geometric shapes (polygons, ellipses). Two comprehensive measures, one each for detection and tracking, are proposed and substantiated to capture different aspects of the task in a single score. We choose text detection and tracking tasks to show the effectiveness of our evaluation framework. Results are presented from evaluations of existing algorithms using real world data and the metrics are shown to be effective in measuring the total accuracy of these detection and tracking algorithms.</div></front></TEI><affiliations><list><country><li>États-Unis</li></country><region><li>Floride</li><li>Maryland</li><li>Pennsylvanie</li></region></list><tree><country name="États-Unis"><region name="Floride"><name sortKey="Manohar, Vasant" sort="Manohar, Vasant" uniqKey="Manohar V" first="Vasant" last="Manohar">Vasant Manohar</name></region><name sortKey="Boonstra, Matthew" sort="Boonstra, Matthew" uniqKey="Boonstra M" first="Matthew" last="Boonstra">Matthew Boonstra</name><name sortKey="Boonstra, Matthew" sort="Boonstra, Matthew" uniqKey="Boonstra M" first="Matthew" last="Boonstra">Matthew Boonstra</name><name sortKey="Garofolo, John" sort="Garofolo, John" uniqKey="Garofolo J" first="John" last="Garofolo">John Garofolo</name><name sortKey="Goldgof, Dmitry" sort="Goldgof, Dmitry" uniqKey="Goldgof D" first="Dmitry" last="Goldgof">Dmitry Goldgof</name><name sortKey="Goldgof, Dmitry" sort="Goldgof, Dmitry" uniqKey="Goldgof D" first="Dmitry" last="Goldgof">Dmitry Goldgof</name><name sortKey="Kasturi, Rangachar" sort="Kasturi, Rangachar" uniqKey="Kasturi R" first="Rangachar" last="Kasturi">Rangachar Kasturi</name><name sortKey="Kasturi, Rangachar" sort="Kasturi, Rangachar" uniqKey="Kasturi R" first="Rangachar" last="Kasturi">Rangachar Kasturi</name><name sortKey="Manohar, Vasant" sort="Manohar, Vasant" uniqKey="Manohar V" first="Vasant" last="Manohar">Vasant Manohar</name><name sortKey="Raju, Harish" sort="Raju, Harish" uniqKey="Raju H" first="Harish" last="Raju">Harish Raju</name><name sortKey="Soundararajan, Padmanabhan" sort="Soundararajan, Padmanabhan" uniqKey="Soundararajan P" first="Padmanabhan" last="Soundararajan">Padmanabhan Soundararajan</name><name sortKey="Soundararajan, Padmanabhan" sort="Soundararajan, Padmanabhan" uniqKey="Soundararajan P" first="Padmanabhan" last="Soundararajan">Padmanabhan Soundararajan</name></country></tree></affiliations></record>Pour manipuler ce document sous Unix (Dilib)
EXPLOR_STEP=$WICRI_ROOT/Ticri/CIDE/explor/OcrV1/Data/Main/Exploration
HfdSelect -h $EXPLOR_STEP/biblio.hfd -nk 001028 | SxmlIndent | more
Ou
HfdSelect -h $EXPLOR_AREA/Data/Main/Exploration/biblio.hfd -nk 001028 | SxmlIndent | more
Pour mettre un lien sur cette page dans le réseau Wicri
{{Explor lien
|wiki= Ticri/CIDE
|area= OcrV1
|flux= Main
|étape= Exploration
|type= RBID
|clé= ISTEX:D6D2390262CD9AEA06063F8AF743A0799CC6A87A
|texte= Performance Evaluation of Text Detection and Tracking in Video
}}
| This area was generated with Dilib version V0.6.32. |  |