Exemplar Based Recognition of Visual Shapes

TY - GEN

T1 - Exemplar Based Recognition of Visual Shapes

AU - Olsen, Søren I.

N1 - Conference code: 14

PY - 2005

Y1 - 2005

N2 - 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.

AB - 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.

U2 - 10.1007/11499145_86

DO - 10.1007/11499145_86

M3 - Article in proceedings

SN - 978-3-540-26320-3

T3 - Lecture notes in computer science

SP - 852

EP - 861

BT - Image Analysis

PB - <Forlag uden navn>

T2 - 14th Scandinavian Conference in Image Analysis (SCIA)

Y2 - 29 November 2010

ER -