Contour Grouping and Object-Based Attention with Saliency Maps
Summary :
The key problem of object-based attention is the definition of objects, while contour grouping methods aim at detecting the complete boundaries of objects in images. In this paper, we develop a new contour grouping method which shows several characteristics. First, it is guided by the global saliency information. By detecting multiple boundaries in a hierarchical way, we actually construct an object-based attention model. Second, it is optimized by the grouping cost, which is decided both by Gestalt cues of directed tangents and by region saliency. Third, it gives a new definition of Gestalt cues for tangents which includes image information as well as tangent information. In this way, we can improve the robustness of our model against noise. Experiment results are shown in this paper, with a comparison against other grouping model and space-based attention model.
- Publication
- IEICE TRANSACTIONS on Information Vol.E92-D No.12 pp.2531-2534
- Publication Date
- 2009/12/01
- Publicized
- Online ISSN
- 1745-1361
- DOI
- 10.1587/transinf.E92.D.2531
- Type of Manuscript
- LETTER
- Category
- Pattern Recognition
Authors
Keyword
Latest Issue
Copyrights notice of machine-translated contents
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Cite this
Copy
Jingjing ZHONG, Siwei LUO, Jiao WANG, "Contour Grouping and Object-Based Attention with Saliency Maps" in IEICE TRANSACTIONS on Information,
vol. E92-D, no. 12, pp. 2531-2534, December 2009, doi: 10.1587/transinf.E92.D.2531.
Abstract: The key problem of object-based attention is the definition of objects, while contour grouping methods aim at detecting the complete boundaries of objects in images. In this paper, we develop a new contour grouping method which shows several characteristics. First, it is guided by the global saliency information. By detecting multiple boundaries in a hierarchical way, we actually construct an object-based attention model. Second, it is optimized by the grouping cost, which is decided both by Gestalt cues of directed tangents and by region saliency. Third, it gives a new definition of Gestalt cues for tangents which includes image information as well as tangent information. In this way, we can improve the robustness of our model against noise. Experiment results are shown in this paper, with a comparison against other grouping model and space-based attention model.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.E92.D.2531/_p
Copy
@ARTICLE{e92-d_12_2531,
author={Jingjing ZHONG, Siwei LUO, Jiao WANG, },
journal={IEICE TRANSACTIONS on Information},
title={Contour Grouping and Object-Based Attention with Saliency Maps},
year={2009},
volume={E92-D},
number={12},
pages={2531-2534},
abstract={The key problem of object-based attention is the definition of objects, while contour grouping methods aim at detecting the complete boundaries of objects in images. In this paper, we develop a new contour grouping method which shows several characteristics. First, it is guided by the global saliency information. By detecting multiple boundaries in a hierarchical way, we actually construct an object-based attention model. Second, it is optimized by the grouping cost, which is decided both by Gestalt cues of directed tangents and by region saliency. Third, it gives a new definition of Gestalt cues for tangents which includes image information as well as tangent information. In this way, we can improve the robustness of our model against noise. Experiment results are shown in this paper, with a comparison against other grouping model and space-based attention model.},
keywords={},
doi={10.1587/transinf.E92.D.2531},
ISSN={1745-1361},
month={December},}
Copy
TY - JOUR
TI - Contour Grouping and Object-Based Attention with Saliency Maps
T2 - IEICE TRANSACTIONS on Information
SP - 2531
EP - 2534
AU - Jingjing ZHONG
AU - Siwei LUO
AU - Jiao WANG
PY - 2009
DO - 10.1587/transinf.E92.D.2531
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E92-D
IS - 12
JA - IEICE TRANSACTIONS on Information
Y1 - December 2009
AB - The key problem of object-based attention is the definition of objects, while contour grouping methods aim at detecting the complete boundaries of objects in images. In this paper, we develop a new contour grouping method which shows several characteristics. First, it is guided by the global saliency information. By detecting multiple boundaries in a hierarchical way, we actually construct an object-based attention model. Second, it is optimized by the grouping cost, which is decided both by Gestalt cues of directed tangents and by region saliency. Third, it gives a new definition of Gestalt cues for tangents which includes image information as well as tangent information. In this way, we can improve the robustness of our model against noise. Experiment results are shown in this paper, with a comparison against other grouping model and space-based attention model.
ER -
English
