Please use this identifier to cite or link to this item:
Scopus Web of Science® Altmetric
Type: Conference paper
Title: What parts of a shape are discriminative?
Author: Premachandran, V.
Kakarala, R.
Citation: Proceedings / ICIP ... International Conference on Image Processing, 2013, pp.2857-2861
Publisher: IEEE
Issue Date: 2013
Series/Report no.: IEEE International Conference on Image Processing ICIP
ISBN: 9781479923410
ISSN: 1522-4880
Conference Name: 20th IEEE International Conference on Image Processing (ICIP 2013) (15 Sep 2013 - 18 Sep 2013 : Melbourne, Australia)
Statement of
Vittal Premachandran and Ramakrishna Kakarala
Abstract: Shape is a distinguishing feature of objects. But when objects have similar global shapes, discriminating them becomes difficult. This calls for the identification of important parts of the shapes. In this paper, we introduce the concept of discriminative parts and propose a method to identify the same. We show how levels of importance can be assigned to different regions of contours, based on their discriminative capability. Our experiments show that the method is promising and can identify semantically meaningful segments as being important segments.
Keywords: Shape
Image Retrieval
Object Recognition
Rights: ©2013 IEEE
DOI: 10.1109/ICIP.2013.6738588
Published version:
Appears in Collections:Aurora harvest 3
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.