Ansatte – Københavns Universitet

Exemplar Based Recognition of Visual Shapes

Publikation: Bidrag til bog/antologi/rapportKonferencebidrag i proceedingsForskningfagfællebedømt

This paper presents an approach of visual shape recognition based on exemplars of attributed keypoints. Training is performed by storing exemplars of keypoints detected in labeled training images. Recognition is made by keypoint matching and voting according to the labels for the matched keypoints. The matching is insensitive to rotations, limited scalings and small deformations. The recognition is robust to noise, background clutter and partial occlusion. Recognition is possible from few training images and improve with the number of training images.
OriginalsprogEngelsk
TitelImage Analysis
Forlag
Publikationsdato2005
Sider852-861
ISBN (Trykt)978-3-540-26320-3
DOI
StatusUdgivet - 2005
Begivenhed14th Scandinavian Conference in Image Analysis (SCIA) - Joensuu, Finland
Varighed: 29 nov. 2010 → …
Konferencens nummer: 14

Konference

Konference14th Scandinavian Conference in Image Analysis (SCIA)
Nummer14
LandFinland
ByJoensuu
Periode29/11/2010 → …
NavnLecture notes in computer science
Vol/bind3540/2005
ISSN0302-9743

Bibliografisk note

Poster Presentations 2: Pattern Recognition, Image Processing, and Applications

ID: 4980005