Flexible spatial configuration of local image features

Local image features have been designed to be informative and repeatable under rigid transformations and illumination deformations. Even though current state-of-the-art local image features present a high degree of repeatability, their local appearance alone usually does not bring enough discriminat...

Ausführliche Beschreibung

Bibliographische Detailangaben
Veröffentlicht in:IEEE transactions on pattern analysis and machine intelligence. - 1979. - 29(2007), 12 vom: 14. Dez., Seite 2089-104
1. Verfasser: Carneiro, Gustavo (VerfasserIn)
Weitere Verfasser: Jepson, Allan D
Format: Aufsatz
Sprache:English
Veröffentlicht: 2007
Zugriff auf das übergeordnete Werk:IEEE transactions on pattern analysis and machine intelligence
Schlagworte:Journal Article
LEADER 01000naa a22002652 4500
001 NLM174366922
003 DE-627
005 20231223135750.0
007 tu
008 231223s2007 xx ||||| 00| ||eng c
028 5 2 |a pubmed24n0581.xml 
035 |a (DE-627)NLM174366922 
035 |a (NLM)17934220 
040 |a DE-627  |b ger  |c DE-627  |e rakwb 
041 |a eng 
100 1 |a Carneiro, Gustavo  |e verfasserin  |4 aut 
245 1 0 |a Flexible spatial configuration of local image features 
264 1 |c 2007 
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 18.12.2007 
500 |a Date Revised 15.10.2007 
500 |a published: Print 
500 |a Citation Status MEDLINE 
520 |a Local image features have been designed to be informative and repeatable under rigid transformations and illumination deformations. Even though current state-of-the-art local image features present a high degree of repeatability, their local appearance alone usually does not bring enough discriminative power to support a reliable matching, resulting in a relatively high number of mismatches in the correspondence set formed during the data association procedure. As a result, geometric filters, commonly based on global spatial configuration, have been used to reduce this number of mismatches. However, this approach presents a trade off between the effectiveness to reject mismatches and the robustness to non-rigid deformations. In this paper, we propose two geometric filters, based on semilocal spatial configuration of local features, that are designed to be robust to non-rigid deformations and to rigid transformations, without compromising its efficacy to reject mismatches. We compare our methods to the Hough transform, which is an efficient and effective mismatch rejection step based on global spatial configuration of features. In these comparisons, our methods are shown to be more effective in the task of rejecting mismatches for rigid transformations and non-rigid deformations at comparable time complexity figures. Finally, we demonstrate how to integrate these methods in a probabilistic recognition system such that the final verification step uses not only the similarity between features, but also their semi-local configuration 
650 4 |a Journal Article 
700 1 |a Jepson, Allan D  |e verfasserin  |4 aut 
773 0 8 |i Enthalten in  |t IEEE transactions on pattern analysis and machine intelligence  |d 1979  |g 29(2007), 12 vom: 14. Dez., Seite 2089-104  |w (DE-627)NLM098212257  |x 1939-3539  |7 nnns 
773 1 8 |g volume:29  |g year:2007  |g number:12  |g day:14  |g month:12  |g pages:2089-104 
912 |a GBV_USEFLAG_A 
912 |a SYSFLAG_A 
912 |a GBV_NLM 
912 |a GBV_ILN_350 
951 |a AR 
952 |d 29  |j 2007  |e 12  |b 14  |c 12  |h 2089-104