End-Stop Exemplar Based Recognition

Publikation: Bidrag til bog/antologi/rapportKonferencebidrag i proceedings

An approach to exemplar based recognition of visual shapes is presented. The shape information is described by attributed interest points (keys) detected by an end-stop operator. The attributes describe the statistics of lines and edges local to the interest point, the position of neighboring interest points, and (in the training phase) a list of recognition names. Recognition is made by a simple voting procedure. Preliminary experiments indicate that the recognition is robust to noise, small deformations, background clutter and partial occlusion.
OriginalsprogEngelsk
TitelImage Analysis : 13th Scandinavian Conference, SCIA 2003 Halmstad, Sweden, June 29 – July 2, 2003 Proceedings
Publikationsdato2003
Sider257-266
DOI
StatusUdgivet - 2003
Begivenhed13th Scandinavian Conference in Image Analysis - SCIA - Halmstad, Sverige
Varighed: 29 nov. 2010 → …
Konferencens nummer: 13

Konference

Konference13th Scandinavian Conference in Image Analysis - SCIA
Nummer13
LandSverige
ByHalmstad
Periode29/11/2010 → …
NavnLecture notes in computer science
Vol/bind2749/2003
ISSN0302-9743

ID: 5581343