Please use this identifier to cite or link to this item:
Title: Contour-based recognition
Authors: Xu, Y.
Quan, Y.
Zhang, Z.
Ji, H. 
Fermuller, C.
Nishigaki, M.
Dementhon, D.
Issue Date: 2012
Source: Xu, Y.,Quan, Y.,Zhang, Z.,Ji, H.,Fermuller, C.,Nishigaki, M.,Dementhon, D. (2012). Contour-based recognition. Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition : 3402-3409. ScholarBank@NUS Repository.
Abstract: Contour is an important cue for object recognition. In this paper, built upon the concept of torque in image space, we propose a new contour-related feature to detect and describe local contour information in images. There are two components for our proposed feature: One is a contour patch detector for detecting image patches with interesting information of object contour, which we call the Maximal/Minimal Torque Patch (MTP) detector. The other is a contour patch descriptor for characterizing a contour patch by sampling the torque values, which we call the Multi-scale Torque (MST) descriptor. Experiments for object recognition on the Caltech-101 dataset showed that the proposed contour feature outperforms other contour-related features and is on a par with many other types of features. When combing our descriptor with the complementary SIFT descriptor, impressive recognition results are observed. © 2012 IEEE.
Source Title: Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
ISBN: 9781467312264
ISSN: 10636919
DOI: 10.1109/CVPR.2012.6248080
Appears in Collections:Staff Publications

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


checked on Mar 7, 2018

Page view(s)

checked on Mar 9, 2018

Google ScholarTM



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