Skeletal shape abstraction from examples

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...

Ausführliche Beschreibung

Bibliographische Detailangaben
Veröffentlicht in:IEEE transactions on pattern analysis and machine intelligence. - 1979. - 31(2009), 5 vom: 01. Mai, Seite 944-52
1. Verfasser: Fatih Demirci, M (VerfasserIn)
Weitere Verfasser: Shokoufandeh, Ali, Dickinson, Sven J
Format: Online-Aufsatz
Sprache:English
Veröffentlicht: 2009
Zugriff auf das übergeordnete Werk:IEEE transactions on pattern analysis and machine intelligence
Schlagworte:Journal Article Research Support, Non-U.S. Gov't
LEADER 01000naa a22002652 4500
001 NLM187210454
003 DE-627
005 20231223175619.0
007 cr uuu---uuuuu
008 231223s2009 xx |||||o 00| ||eng c
024 7 |a 10.1109/TPAMI.2008.267  |2 doi 
028 5 2 |a pubmed24n0624.xml 
035 |a (DE-627)NLM187210454 
035 |a (NLM)19299866 
040 |a DE-627  |b ger  |c DE-627  |e rakwb 
041 |a eng 
100 1 |a Fatih Demirci, M  |e verfasserin  |4 aut 
245 1 0 |a Skeletal shape abstraction from examples 
264 1 |c 2009 
336 |a Text  |b txt  |2 rdacontent 
337 |a ƒaComputermedien  |b c  |2 rdamedia 
338 |a ƒa Online-Ressource  |b cr  |2 rdacarrier 
500 |a Date Completed 10.06.2009 
500 |a Date Revised 20.03.2009 
500 |a published: Print 
500 |a Citation Status MEDLINE 
520 |a 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 
650 4 |a Journal Article 
650 4 |a Research Support, Non-U.S. Gov't 
700 1 |a Shokoufandeh, Ali  |e verfasserin  |4 aut 
700 1 |a Dickinson, Sven J  |e verfasserin  |4 aut 
773 0 8 |i Enthalten in  |t IEEE transactions on pattern analysis and machine intelligence  |d 1979  |g 31(2009), 5 vom: 01. Mai, Seite 944-52  |w (DE-627)NLM098212257  |x 1939-3539  |7 nnns 
773 1 8 |g volume:31  |g year:2009  |g number:5  |g day:01  |g month:05  |g pages:944-52 
856 4 0 |u http://dx.doi.org/10.1109/TPAMI.2008.267  |3 Volltext 
912 |a GBV_USEFLAG_A 
912 |a SYSFLAG_A 
912 |a GBV_NLM 
912 |a GBV_ILN_350 
951 |a AR 
952 |d 31  |j 2009  |e 5  |b 01  |c 05  |h 944-52