Spatially-Sensitive Affine-Invariant Image Descriptors
Identifieur interne : 000E59 ( Main/Exploration ); précédent : 000E58; suivant : 000E60Spatially-Sensitive Affine-Invariant Image Descriptors
Auteurs : M. Bronstein ; M. BronsteinSource :
- Lecture Notes in Computer Science [ 0302-9743 ] ; 2010.
Abstract
Abstract: Invariant image descriptors play an important role in many computer vision and pattern recognition problems such as image search and retrieval. A dominant paradigm today is that of “bags of features”, a representation of images as distributions of primitive visual elements. The main disadvantage of this approach is the loss of spatial relations between features, which often carry important information about the image. In this paper, we show how to construct spatially-sensitive image descriptors in which both the features and their relation are affine-invariant. Our construction is based on a vocabulary of pairs of features coupled with a vocabulary of invariant spatial relations between the features. Experimental results show the advantage of our approach in image retrieval applications.
Url:
DOI: 10.1007/978-3-642-15552-9_15
Affiliations:
Links toward previous steps (curation, corpus...)
- to stream Istex, to step Corpus: 000F88
- to stream Istex, to step Curation: 000F88
- to stream Istex, to step Checkpoint: 000231
- to stream Main, to step Merge: 000E69
- to stream Main, to step Curation: 000E59
Le document en format XML
<record><TEI wicri:istexFullTextTei="biblStruct"><teiHeader><fileDesc><titleStmt><title xml:lang="en">Spatially-Sensitive Affine-Invariant Image Descriptors</title><author><name sortKey="Bronstein, M" sort="Bronstein, M" uniqKey="Bronstein M" first="M." last="Bronstein">M. Bronstein</name></author><author><name sortKey="Bronstein, M" sort="Bronstein, M" uniqKey="Bronstein M" first="M." last="Bronstein">M. Bronstein</name></author></titleStmt><publicationStmt><idno type="wicri:source">ISTEX</idno><idno type="RBID">ISTEX:D6102826ED3A5E87CBC0B4D3A5A9512FB14D694A</idno><date when="2010" year="2010">2010</date><idno type="doi">10.1007/978-3-642-15552-9_15</idno><idno type="url">https://api.istex.fr/document/D6102826ED3A5E87CBC0B4D3A5A9512FB14D694A/fulltext/pdf</idno><idno type="wicri:Area/Istex/Corpus">000F88</idno><idno type="wicri:Area/Istex/Curation">000F88</idno><idno type="wicri:Area/Istex/Checkpoint">000231</idno><idno type="wicri:doubleKey">0302-9743:2010:Bronstein M:spatially:sensitive:affine</idno><idno type="wicri:Area/Main/Merge">000E69</idno><idno type="wicri:Area/Main/Curation">000E59</idno><idno type="wicri:Area/Main/Exploration">000E59</idno></publicationStmt><sourceDesc><biblStruct><analytic><title level="a" type="main" xml:lang="en">Spatially-Sensitive Affine-Invariant Image Descriptors</title><author><name sortKey="Bronstein, M" sort="Bronstein, M" uniqKey="Bronstein M" first="M." last="Bronstein">M. Bronstein</name><affiliation><wicri:noCountry code="no comma">BBK Technologies ltd</wicri:noCountry></affiliation><affiliation><wicri:noCountry code="subField">Tel Aviv University</wicri:noCountry></affiliation></author><author><name sortKey="Bronstein, M" sort="Bronstein, M" uniqKey="Bronstein M" first="M." last="Bronstein">M. Bronstein</name><affiliation><wicri:noCountry code="no comma">BBK Technologies ltd</wicri:noCountry></affiliation><affiliation><wicri:noCountry code="subField">Israel Institute of Technology</wicri:noCountry></affiliation></author></analytic><monogr></monogr><series><title level="s">Lecture Notes in Computer Science</title><imprint><date>2010</date></imprint><idno type="ISSN">0302-9743</idno><idno type="eISSN">1611-3349</idno><idno type="ISSN">0302-9743</idno></series><idno type="istex">D6102826ED3A5E87CBC0B4D3A5A9512FB14D694A</idno><idno type="DOI">10.1007/978-3-642-15552-9_15</idno><idno type="ChapterID">Chap15</idno><idno type="ChapterID">15</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: Invariant image descriptors play an important role in many computer vision and pattern recognition problems such as image search and retrieval. A dominant paradigm today is that of “bags of features”, a representation of images as distributions of primitive visual elements. The main disadvantage of this approach is the loss of spatial relations between features, which often carry important information about the image. In this paper, we show how to construct spatially-sensitive image descriptors in which both the features and their relation are affine-invariant. Our construction is based on a vocabulary of pairs of features coupled with a vocabulary of invariant spatial relations between the features. Experimental results show the advantage of our approach in image retrieval applications.</div></front></TEI><affiliations><list></list><tree><noCountry><name sortKey="Bronstein, M" sort="Bronstein, M" uniqKey="Bronstein M" first="M." last="Bronstein">M. Bronstein</name><name sortKey="Bronstein, M" sort="Bronstein, M" uniqKey="Bronstein M" first="M." last="Bronstein">M. Bronstein</name></noCountry></tree></affiliations></record>Pour manipuler ce document sous Unix (Dilib)
EXPLOR_STEP=$WICRI_ROOT/Wicri/Musique/explor/OperaV1/Data/Main/Exploration
HfdSelect -h $EXPLOR_STEP/biblio.hfd -nk 000E59 | SxmlIndent | more
Ou
HfdSelect -h $EXPLOR_AREA/Data/Main/Exploration/biblio.hfd -nk 000E59 | SxmlIndent | more
Pour mettre un lien sur cette page dans le réseau Wicri
{{Explor lien
|wiki= Wicri/Musique
|area= OperaV1
|flux= Main
|étape= Exploration
|type= RBID
|clé= ISTEX:D6102826ED3A5E87CBC0B4D3A5A9512FB14D694A
|texte= Spatially-Sensitive Affine-Invariant Image Descriptors
}}
| This area was generated with Dilib version V0.6.21. |  |