Content-Adaptive Superpixel Segmentation

Superpixel segmentation targets at grouping pixels in an image into atomic regions whose boundaries align well with the natural object boundaries. This paper first proposes a new feature representation for superpixel segmentation that holistically embraces color, contour, texture, and spatial featur...

Ausführliche Beschreibung

Bibliographische Detailangaben
Veröffentlicht in:IEEE transactions on image processing : a publication of the IEEE Signal Processing Society. - 1992. - 27(2018), 6 vom: 27. Juni, Seite 2883-2896
1. Verfasser: Xiao, Xiaolin (VerfasserIn)
Weitere Verfasser: Zhou, Yicong, Gong, Yue-Jiao
Format: Online-Aufsatz
Sprache:English
Veröffentlicht: 2018
Zugriff auf das übergeordnete Werk:IEEE transactions on image processing : a publication of the IEEE Signal Processing Society
Schlagworte:Journal Article
LEADER 01000naa a22002652 4500
001 NLM282255435
003 DE-627
005 20231225033514.0
007 cr uuu---uuuuu
008 231225s2018 xx |||||o 00| ||eng c
024 7 |a 10.1109/TIP.2018.2810541  |2 doi 
028 5 2 |a pubmed24n0940.xml 
035 |a (DE-627)NLM282255435 
035 |a (NLM)29570089 
040 |a DE-627  |b ger  |c DE-627  |e rakwb 
041 |a eng 
100 1 |a Xiao, Xiaolin  |e verfasserin  |4 aut 
245 1 0 |a Content-Adaptive Superpixel Segmentation 
264 1 |c 2018 
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 30.07.2018 
500 |a Date Revised 30.07.2018 
500 |a published: Print 
500 |a Citation Status PubMed-not-MEDLINE 
520 |a Superpixel segmentation targets at grouping pixels in an image into atomic regions whose boundaries align well with the natural object boundaries. This paper first proposes a new feature representation for superpixel segmentation that holistically embraces color, contour, texture, and spatial features. Then, we introduce a clustering-based discriminability measure to iteratively evaluate the importance of different features. Integrating the feature representation and the discriminability measure, we propose a novel content-adaptive superpixel (CAS) segmentation algorithm. CAS is able to automatically and iteratively adjust the weights of different features to fit various properties of image instances. Experiments on several challenging datasets demonstrate that the proposed CAS outperforms the state-of-the-art methods and has a low computational cost 
650 4 |a Journal Article 
700 1 |a Zhou, Yicong  |e verfasserin  |4 aut 
700 1 |a Gong, Yue-Jiao  |e verfasserin  |4 aut 
773 0 8 |i Enthalten in  |t IEEE transactions on image processing : a publication of the IEEE Signal Processing Society  |d 1992  |g 27(2018), 6 vom: 27. Juni, Seite 2883-2896  |w (DE-627)NLM09821456X  |x 1941-0042  |7 nnns 
773 1 8 |g volume:27  |g year:2018  |g number:6  |g day:27  |g month:06  |g pages:2883-2896 
856 4 0 |u http://dx.doi.org/10.1109/TIP.2018.2810541  |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 27  |j 2018  |e 6  |b 27  |c 06  |h 2883-2896