Contour Detection by Synchronization of Integrate-and-Fire Neurons
Identifieur interne : 008349 ( Main/Exploration ); précédent : 008348; suivant : 008350Contour Detection by Synchronization of Integrate-and-Fire Neurons
Auteurs : Etienne Hugues ; Florent Guilleux ; Olivier RochelSource :
English descriptors
- KwdEn :
Abstract
We present a biologically inspired spiking neural network which is able to detect contours in grey level images by synchronization of neurons. This network is made of integrate-and-fire neurons, spaced on a triangular network, whose oriented receptive field is constructed by a wavelet which specifically detects edges. The neurons are excitatorily and locally connected between receptive fields that tend to detect the same contour. A contour, if its width is not too large, activates a chain of neurons, with some heterogeneity in the inputs. The capacity of a chain to synchronize with respect to such heterogeneity is studied. Synchronization on a contour is found to be possible for a sufficiently large width.
Affiliations:
Links toward previous steps (curation, corpus...)
- to stream Crin, to step Corpus: 003607
- to stream Crin, to step Curation: 003607
- to stream Crin, to step Checkpoint: 001037
- to stream Main, to step Merge: 008805
- to stream Main, to step Curation: 008349
Le document en format XML
<record><TEI><teiHeader><fileDesc><titleStmt><title xml:lang="en" wicri:score="481">Contour Detection by Synchronization of Integrate-and-Fire Neurons</title>
</titleStmt>
<publicationStmt><idno type="RBID">CRIN:hugues02a</idno>
<date when="2002" year="2002">2002</date>
<idno type="wicri:Area/Crin/Corpus">003607</idno>
<idno type="wicri:Area/Crin/Curation">003607</idno>
<idno type="wicri:explorRef" wicri:stream="Crin" wicri:step="Curation">003607</idno>
<idno type="wicri:Area/Crin/Checkpoint">001037</idno>
<idno type="wicri:explorRef" wicri:stream="Crin" wicri:step="Checkpoint">001037</idno>
<idno type="wicri:Area/Main/Merge">008805</idno>
<idno type="wicri:Area/Main/Curation">008349</idno>
<idno type="wicri:Area/Main/Exploration">008349</idno>
</publicationStmt>
<sourceDesc><biblStruct><analytic><title xml:lang="en">Contour Detection by Synchronization of Integrate-and-Fire Neurons</title>
<author><name sortKey="Hugues, Etienne" sort="Hugues, Etienne" uniqKey="Hugues E" first="Etienne" last="Hugues">Etienne Hugues</name>
</author>
<author><name sortKey="Guilleux, Florent" sort="Guilleux, Florent" uniqKey="Guilleux F" first="Florent" last="Guilleux">Florent Guilleux</name>
</author>
<author><name sortKey="Rochel, Olivier" sort="Rochel, Olivier" uniqKey="Rochel O" first="Olivier" last="Rochel">Olivier Rochel</name>
</author>
</analytic>
</biblStruct>
</sourceDesc>
</fileDesc>
<profileDesc><textClass><keywords scheme="KwdEn" xml:lang="en"><term>contour detection</term>
<term>integrate-and-fire</term>
<term>neural network</term>
<term>orientation selectivity</term>
<term>spiking neuron</term>
<term>synchronization</term>
<term>temporal code</term>
</keywords>
</textClass>
</profileDesc>
</teiHeader>
<front><div type="abstract" xml:lang="en" wicri:score="2842">We present a biologically inspired spiking neural network which is able to detect contours in grey level images by synchronization of neurons. This network is made of integrate-and-fire neurons, spaced on a triangular network, whose oriented receptive field is constructed by a wavelet which specifically detects edges. The neurons are excitatorily and locally connected between receptive fields that tend to detect the same contour. A contour, if its width is not too large, activates a chain of neurons, with some heterogeneity in the inputs. The capacity of a chain to synchronize with respect to such heterogeneity is studied. Synchronization on a contour is found to be possible for a sufficiently large width.</div>
</front>
</TEI>
<affiliations><list></list>
<tree><noCountry><name sortKey="Guilleux, Florent" sort="Guilleux, Florent" uniqKey="Guilleux F" first="Florent" last="Guilleux">Florent Guilleux</name>
<name sortKey="Hugues, Etienne" sort="Hugues, Etienne" uniqKey="Hugues E" first="Etienne" last="Hugues">Etienne Hugues</name>
<name sortKey="Rochel, Olivier" sort="Rochel, Olivier" uniqKey="Rochel O" first="Olivier" last="Rochel">Olivier Rochel</name>
</noCountry>
</tree>
</affiliations>
</record>
Pour manipuler ce document sous Unix (Dilib)
EXPLOR_STEP=$WICRI_ROOT/Wicri/Lorraine/explor/InforLorV4/Data/Main/Exploration
HfdSelect -h $EXPLOR_STEP/biblio.hfd -nk 008349 | SxmlIndent | more
Ou
HfdSelect -h $EXPLOR_AREA/Data/Main/Exploration/biblio.hfd -nk 008349 | SxmlIndent | more
Pour mettre un lien sur cette page dans le réseau Wicri
{{Explor lien |wiki= Wicri/Lorraine |area= InforLorV4 |flux= Main |étape= Exploration |type= RBID |clé= CRIN:hugues02a |texte= Contour Detection by Synchronization of Integrate-and-Fire Neurons }}
![]() | This area was generated with Dilib version V0.6.33. | ![]() |