File Download
Links for fulltext
(May Require Subscription)
- Publisher Website: 10.1109/CVPR.2012.6247725
- Scopus: eid_2-s2.0-84866689544
- Find via
Supplementary
-
Citations:
- Scopus: 0
- Appears in Collections:
Conference Paper: Learning image-specific parameters for interactive segmentation
Title | Learning image-specific parameters for interactive segmentation |
---|---|
Authors | |
Keywords | Approximation scheme Conditional random field Cutting plane methods Energy margin Interactive image segmentation |
Issue Date | 2012 |
Publisher | IEEE Computer Society. The Journal's web site is located at http://ieeexplore.ieee.org/xpl/conhome.jsp?punumber=1000147 |
Citation | The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Providence, RI., 16-21 June 2012. In IEEE Conference on Computer Vision and Pattern Recognition Proceedings, 2012, p. 590-597 How to Cite? |
Abstract | In this paper, we present a novel interactive image segmentation technique that automatically learns segmentation parameters tailored for each and every image. Unlike existing work, our method does not require any offline parameter tuning or training stage, and is capable of determining image-specific parameters according to some simple user interactions with the target image. We formulate the segmentation problem as an inference of a conditional random field (CRF) over a segmentation mask and the target image, and parametrize this CRF by different weights (e.g., color, texture and smoothing). The weight parameters are learned via an energy margin maximization, which is solved using a constraint approximation scheme and the cutting plane method. Experimental results show that our method, by learning image-specific parameters automatically, outperforms other state-of-the-art interactive image segmentation techniques. © 2012 IEEE. |
Description | Posters 1B - Color and Texture, Early & Biological Vision, Image Based Modeling, Segmentation and Grouping |
Persistent Identifier | http://hdl.handle.net/10722/152969 |
ISBN | |
ISSN | 2023 SCImago Journal Rankings: 10.331 |
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Kuang, Z | en_US |
dc.contributor.author | Schnieders, D | en_US |
dc.contributor.author | Zhou, H | en_US |
dc.contributor.author | Wong, KKY | en_US |
dc.contributor.author | Yu, Y | en_US |
dc.contributor.author | Peng, B | en_US |
dc.date.accessioned | 2012-07-16T09:53:34Z | - |
dc.date.available | 2012-07-16T09:53:34Z | - |
dc.date.issued | 2012 | en_US |
dc.identifier.citation | The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Providence, RI., 16-21 June 2012. In IEEE Conference on Computer Vision and Pattern Recognition Proceedings, 2012, p. 590-597 | en_US |
dc.identifier.isbn | 978-1-4673-1228-8 | - |
dc.identifier.issn | 1063-6919 | - |
dc.identifier.uri | http://hdl.handle.net/10722/152969 | - |
dc.description | Posters 1B - Color and Texture, Early & Biological Vision, Image Based Modeling, Segmentation and Grouping | - |
dc.description.abstract | In this paper, we present a novel interactive image segmentation technique that automatically learns segmentation parameters tailored for each and every image. Unlike existing work, our method does not require any offline parameter tuning or training stage, and is capable of determining image-specific parameters according to some simple user interactions with the target image. We formulate the segmentation problem as an inference of a conditional random field (CRF) over a segmentation mask and the target image, and parametrize this CRF by different weights (e.g., color, texture and smoothing). The weight parameters are learned via an energy margin maximization, which is solved using a constraint approximation scheme and the cutting plane method. Experimental results show that our method, by learning image-specific parameters automatically, outperforms other state-of-the-art interactive image segmentation techniques. © 2012 IEEE. | - |
dc.language | eng | en_US |
dc.publisher | IEEE Computer Society. The Journal's web site is located at http://ieeexplore.ieee.org/xpl/conhome.jsp?punumber=1000147 | - |
dc.relation.ispartof | IEEE Conference on Computer Vision and Pattern Recognition Proceedings | en_US |
dc.subject | Approximation scheme | - |
dc.subject | Conditional random field | - |
dc.subject | Cutting plane methods | - |
dc.subject | Energy margin | - |
dc.subject | Interactive image segmentation | - |
dc.title | Learning image-specific parameters for interactive segmentation | en_US |
dc.type | Conference_Paper | en_US |
dc.identifier.email | Kuang, Z: kuangzhh@HKUSUC.hku.hk | en_US |
dc.identifier.email | Schnieders, D: scdirk@hku.hk | en_US |
dc.identifier.email | Zhou, H: zhhoper@hku.hk | en_US |
dc.identifier.email | Wong, KKY: kykwong@cs.hku.hk | - |
dc.identifier.email | Yu, Y: yzyu@cs.hku.hk | - |
dc.identifier.authority | Wong, KKY=rp01393 | en_US |
dc.identifier.authority | Yu, Y=rp01415 | en_US |
dc.description.nature | link_to_subscribed_fulltext | - |
dc.identifier.doi | 10.1109/CVPR.2012.6247725 | - |
dc.identifier.scopus | eid_2-s2.0-84866689544 | - |
dc.identifier.hkuros | 200763 | en_US |
dc.identifier.spage | 590 | - |
dc.identifier.epage | 597 | - |
dc.publisher.place | United States | - |
dc.description.other | The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Providence, RI., 16-21 June 2012. In IEEE Conference on Computer Vision and Pattern Recognition Proceedings, 2012, p. 590-597 | - |
dc.identifier.issnl | 1063-6919 | - |