Indexing hierarchical structures using graph spectra

Hierarchical image structures are abundant in computer vision and have been used to encode part structure, scale spaces, and a variety of multiresolution features. In this paper, we describe a framework for indexing such representations that embeds the topological structure of a directed acyclic gra...

Ausführliche Beschreibung

Bibliographische Detailangaben
Veröffentlicht in:IEEE transactions on pattern analysis and machine intelligence. - 1979. - 27(2005), 7 vom: 01. Juli, Seite 1125-40
1. Verfasser: Shokoufandeh, Ali (VerfasserIn)
Weitere Verfasser: Macrini, Diego, Dickinson, Sven, Siddiqi, Kaleem, Zucker, Steven W
Format: Aufsatz
Sprache:English
Veröffentlicht: 2005
Zugriff auf das übergeordnete Werk:IEEE transactions on pattern analysis and machine intelligence
Schlagworte:Comparative Study Evaluation Study Journal Article Research Support, Non-U.S. Gov't Research Support, U.S. Gov't, Non-P.H.S.
LEADER 01000naa a22002652 4500
001 NLM156508362
003 DE-627
005 20231223074311.0
007 tu
008 231223s2005 xx ||||| 00| ||eng c
028 5 2 |a pubmed24n0522.xml 
035 |a (DE-627)NLM156508362 
035 |a (NLM)16013759 
040 |a DE-627  |b ger  |c DE-627  |e rakwb 
041 |a eng 
100 1 |a Shokoufandeh, Ali  |e verfasserin  |4 aut 
245 1 0 |a Indexing hierarchical structures using graph spectra 
264 1 |c 2005 
336 |a Text  |b txt  |2 rdacontent 
337 |a ohne Hilfsmittel zu benutzen  |b n  |2 rdamedia 
338 |a Band  |b nc  |2 rdacarrier 
500 |a Date Completed 11.08.2005 
500 |a Date Revised 10.12.2019 
500 |a published: Print 
500 |a Citation Status MEDLINE 
520 |a Hierarchical image structures are abundant in computer vision and have been used to encode part structure, scale spaces, and a variety of multiresolution features. In this paper, we describe a framework for indexing such representations that embeds the topological structure of a directed acyclic graph (DAG) into a low-dimensional vector space. Based on a novel spectral characterization of a DAG, this topological signature allows us to efficiently retrieve a promising set of candidates from a database of models using a simple nearest-neighbor search. We establish the insensitivity of the signature to minor perturbation of graph structure due to noise, occlusion, or node split/merge. To accommodate large-scale occlusion, the DAG rooted at each nonleaf node of the query "votes" for model objects that share that "part," effectively accumulating local evidence in a model DAG's topological subspaces. We demonstrate the approach with a series of indexing experiments in the domain of view-based 3D object recognition using shock graphs 
650 4 |a Comparative Study 
650 4 |a Evaluation Study 
650 4 |a Journal Article 
650 4 |a Research Support, Non-U.S. Gov't 
650 4 |a Research Support, U.S. Gov't, Non-P.H.S. 
700 1 |a Macrini, Diego  |e verfasserin  |4 aut 
700 1 |a Dickinson, Sven  |e verfasserin  |4 aut 
700 1 |a Siddiqi, Kaleem  |e verfasserin  |4 aut 
700 1 |a Zucker, Steven W  |e verfasserin  |4 aut 
773 0 8 |i Enthalten in  |t IEEE transactions on pattern analysis and machine intelligence  |d 1979  |g 27(2005), 7 vom: 01. Juli, Seite 1125-40  |w (DE-627)NLM098212257  |x 1939-3539  |7 nnns 
773 1 8 |g volume:27  |g year:2005  |g number:7  |g day:01  |g month:07  |g pages:1125-40 
912 |a GBV_USEFLAG_A 
912 |a SYSFLAG_A 
912 |a GBV_NLM 
912 |a GBV_ILN_350 
951 |a AR 
952 |d 27  |j 2005  |e 7  |b 01  |c 07  |h 1125-40