Please use this identifier to cite or link to this item: https://hdl.handle.net/20.500.11851/7469
Title: Skeletal Shape Abstraction from Examples
Authors: Demirci, Muhammed Fatih
Shokoufandeh, Ali
Dickinson, Sven J.
Keywords: Shape abstraction
medial axis graphs
prototype learning
many-to-many graph matching
Publisher: IEEE Computer Soc
Abstract: Learning a class prototype from a set of exemplars is an important challenge facing researchers in object categorization. Although the problem is receiving growing interest, most approaches assume a one-to-one correspondence among local features, restricting their ability to learn true abstractions of a shape. In this paper, we present a new technique for learning an abstract shape prototype from a set of exemplars whose features are in many-to-many correspondence. Focusing on the domain of 2D shape, we represent a silhouette as a medial axis graph whose nodes correspond to "parts" defined by medial branches and whose edges connect adjacent parts. Given a pair of medial axis graphs, we establish a many-to-many correspondence between their nodes to find correspondences among articulating parts. Based on these correspondences, we recover the abstracted medial axis graph along with the positional and radial attributes associated with its nodes. We evaluate the abstracted prototypes in the context of a recognition task.
URI: https://doi.org/10.1109/TPAMI.2008.267
https://hdl.handle.net/20.500.11851/7469
ISSN: 0162-8828
1939-3539
Appears in Collections:Bilgisayar Mühendisliği Bölümü / Department of Computer Engineering
PubMed İndeksli Yayınlar Koleksiyonu / PubMed Indexed Publications Collection
Scopus İndeksli Yayınlar Koleksiyonu / Scopus Indexed Publications Collection
WoS İndeksli Yayınlar Koleksiyonu / WoS Indexed Publications Collection

Show full item record



CORE Recommender

SCOPUSTM   
Citations

46
checked on Mar 23, 2024

WEB OF SCIENCETM
Citations

31
checked on Mar 9, 2024

Page view(s)

54
checked on Mar 25, 2024

Google ScholarTM

Check




Altmetric


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