Please use this identifier to cite or link to this item:
Scopus Web of Science® Altmetric
Type: Journal article
Title: Object detection by global contour shape
Author: Schindler, K.
Suter, D.
Citation: Pattern Recognition, 2008; 41(12):3736-3748
Publisher: Pergamon-Elsevier Science Ltd
Issue Date: 2008
ISSN: 0031-3203
Statement of
Konrad Schindler and David Suter
Abstract: We present a method for object class detection in images based on global shape. A distance measure for elastic shape matching is derived, which is invariant to scale and rotation, and robust against non-parametric deformations. Starting from an over-segmentation of the image, the space of potential object boundaries is explored to find boundaries, which have high similarity with the shape template of the object class to be detected. An extensive experimental evaluation is presented. The approach achieves a remarkable detection rate of 83–91% at 0.2 false positives per image on three challenging data sets
Keywords: Object category detection; Contour matching; Probabilistic shape distance; Region grouping
Description: Copyright © 2008 Elsevier Ltd All rights reserved.
RMID: 0020094054
DOI: 10.1016/j.patcog.2008.05.025
Appears in Collections:Computer Science publications

Files in This Item:
There are no files associated with this item.

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.