Contour detection and hierarchical image segmentation

This paper investigates two fundamental problems in computer vision: contour detection and image segmentation. We present state-of-the-art algorithms for both of these tasks. Our contour detector combines multiple local cues into a globalization framework based on spectral clustering. Our segmentati...

Ausführliche Beschreibung

Bibliographische Detailangaben
Veröffentlicht in:IEEE transactions on pattern analysis and machine intelligence. - 1979. - 33(2011), 5 vom: 15. Mai, Seite 898-916
1. Verfasser: Arbeláez, Pablo (VerfasserIn)
Weitere Verfasser: Maire, Michael, Fowlkes, Charless, Malik, Jitendra
Format: Online-Aufsatz
Sprache:English
Veröffentlicht: 2011
Zugriff auf das übergeordnete Werk:IEEE transactions on pattern analysis and machine intelligence
Schlagworte:Journal Article
LEADER 01000naa a22002652 4500
001 NLM200531441
003 DE-627
005 20231223220741.0
007 cr uuu---uuuuu
008 231223s2011 xx |||||o 00| ||eng c
024 7 |a 10.1109/TPAMI.2010.161  |2 doi 
028 5 2 |a pubmed24n0668.xml 
035 |a (DE-627)NLM200531441 
035 |a (NLM)20733228 
040 |a DE-627  |b ger  |c DE-627  |e rakwb 
041 |a eng 
100 1 |a Arbeláez, Pablo  |e verfasserin  |4 aut 
245 1 0 |a Contour detection and hierarchical image segmentation 
264 1 |c 2011 
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 18.08.2011 
500 |a Date Revised 01.07.2011 
500 |a published: Print 
500 |a Citation Status MEDLINE 
520 |a This paper investigates two fundamental problems in computer vision: contour detection and image segmentation. We present state-of-the-art algorithms for both of these tasks. Our contour detector combines multiple local cues into a globalization framework based on spectral clustering. Our segmentation algorithm consists of generic machinery for transforming the output of any contour detector into a hierarchical region tree. In this manner, we reduce the problem of image segmentation to that of contour detection. Extensive experimental evaluation demonstrates that both our contour detection and segmentation methods significantly outperform competing algorithms. The automatically generated hierarchical segmentations can be interactively refined by user-specified annotations. Computation at multiple image resolutions provides a means of coupling our system to recognition applications 
650 4 |a Journal Article 
700 1 |a Maire, Michael  |e verfasserin  |4 aut 
700 1 |a Fowlkes, Charless  |e verfasserin  |4 aut 
700 1 |a Malik, Jitendra  |e verfasserin  |4 aut 
773 0 8 |i Enthalten in  |t IEEE transactions on pattern analysis and machine intelligence  |d 1979  |g 33(2011), 5 vom: 15. Mai, Seite 898-916  |w (DE-627)NLM098212257  |x 1939-3539  |7 nnns 
773 1 8 |g volume:33  |g year:2011  |g number:5  |g day:15  |g month:05  |g pages:898-916 
856 4 0 |u http://dx.doi.org/10.1109/TPAMI.2010.161  |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 33  |j 2011  |e 5  |b 15  |c 05  |h 898-916