The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. ex. Some numerals are expressed as "XNUMX".
Copyrights notice
The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. Copyrights notice
객체 기반 주의의 핵심 문제는 객체를 정의하는 것인 반면, 윤곽 그룹화 방법은 이미지에서 객체의 완전한 경계를 탐지하는 것을 목표로 합니다. 본 논문에서는 몇 가지 특징을 보이는 새로운 윤곽 그룹화 방법을 개발한다. 첫째, 글로벌 돌출성 정보를 기준으로 한다. 계층적 방식으로 여러 경계를 감지함으로써 실제로 객체 기반 주의 모델을 구성합니다. 둘째, 방향성 접선의 게슈탈트 단서와 지역 돌출성에 의해 결정되는 그룹화 비용에 의해 최적화됩니다. 셋째, 접선 정보뿐만 아니라 이미지 정보도 포함하는 접선에 대한 게슈탈트 단서에 대한 새로운 정의를 제공합니다. 이러한 방식으로 우리는 노이즈에 대한 모델의 견고성을 향상시킬 수 있습니다. 본 논문에서는 실험 결과를 다른 그룹화 모델 및 공간 기반 주의 모델과 비교하여 보여줍니다.
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.
부
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
부
@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},}
부
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 -