We propose a novel threshold-free salient object detection approach which integrates both saliency density and edge response. The salient object with a well-defined boundary can be automatically detected by our approach. Saliency density and edge response maximization is used as the quality function to direct the salient object discovery. The global optimal window containing a salient object is efficiently located through the proposed saliency density and edge response based branch-and-bound search. To extract the salient object with a well-defined boundary, the GrabCut method is applied, initialized by the located window. Experimental results show that our approach outperforms the methods only using saliency or edge response and achieves a comparable performance with the best state-of-the-art method, while being without any threshold or multiple iterations of GrabCut.
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.
Copy
Huiyun JING, Qi HAN, Xin HE, Xiamu NIU, "Saliency Density and Edge Response Based Salient Object Detection" in IEICE TRANSACTIONS on Information,
vol. E96-D, no. 5, pp. 1243-1246, May 2013, doi: 10.1587/transinf.E96.D.1243.
Abstract: We propose a novel threshold-free salient object detection approach which integrates both saliency density and edge response. The salient object with a well-defined boundary can be automatically detected by our approach. Saliency density and edge response maximization is used as the quality function to direct the salient object discovery. The global optimal window containing a salient object is efficiently located through the proposed saliency density and edge response based branch-and-bound search. To extract the salient object with a well-defined boundary, the GrabCut method is applied, initialized by the located window. Experimental results show that our approach outperforms the methods only using saliency or edge response and achieves a comparable performance with the best state-of-the-art method, while being without any threshold or multiple iterations of GrabCut.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.E96.D.1243/_p
Copy
@ARTICLE{e96-d_5_1243,
author={Huiyun JING, Qi HAN, Xin HE, Xiamu NIU, },
journal={IEICE TRANSACTIONS on Information},
title={Saliency Density and Edge Response Based Salient Object Detection},
year={2013},
volume={E96-D},
number={5},
pages={1243-1246},
abstract={We propose a novel threshold-free salient object detection approach which integrates both saliency density and edge response. The salient object with a well-defined boundary can be automatically detected by our approach. Saliency density and edge response maximization is used as the quality function to direct the salient object discovery. The global optimal window containing a salient object is efficiently located through the proposed saliency density and edge response based branch-and-bound search. To extract the salient object with a well-defined boundary, the GrabCut method is applied, initialized by the located window. Experimental results show that our approach outperforms the methods only using saliency or edge response and achieves a comparable performance with the best state-of-the-art method, while being without any threshold or multiple iterations of GrabCut.},
keywords={},
doi={10.1587/transinf.E96.D.1243},
ISSN={1745-1361},
month={May},}
Copy
TY - JOUR
TI - Saliency Density and Edge Response Based Salient Object Detection
T2 - IEICE TRANSACTIONS on Information
SP - 1243
EP - 1246
AU - Huiyun JING
AU - Qi HAN
AU - Xin HE
AU - Xiamu NIU
PY - 2013
DO - 10.1587/transinf.E96.D.1243
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E96-D
IS - 5
JA - IEICE TRANSACTIONS on Information
Y1 - May 2013
AB - We propose a novel threshold-free salient object detection approach which integrates both saliency density and edge response. The salient object with a well-defined boundary can be automatically detected by our approach. Saliency density and edge response maximization is used as the quality function to direct the salient object discovery. The global optimal window containing a salient object is efficiently located through the proposed saliency density and edge response based branch-and-bound search. To extract the salient object with a well-defined boundary, the GrabCut method is applied, initialized by the located window. Experimental results show that our approach outperforms the methods only using saliency or edge response and achieves a comparable performance with the best state-of-the-art method, while being without any threshold or multiple iterations of GrabCut.
ER -