TY - GEN
T1 - Saliency Detection via Background Seeds by Object Proposals
AU - Jian, Muwei
AU - Zhao, Runxia
AU - Dong, Junyu
AU - Lam, Kin Man
PY - 2018/11/12
Y1 - 2018/11/12
N2 - In the recent research of saliency detection, many graph-based algorithms are applied, which use the border of an image as a background query. This frequently leads to undesired errors and retrieval outputs when the boundaries of the salient objects concerned touch, or connect with, the image's border. In this paper, we propose a novel bottom-up saliency-detection algorithm to tackle and overcome the above issue. First, we utilize object proposals to collect the background seeds reliably. Then, the Extended Random Walk algorithm is adopted to propagate the prior background labels to the rest of the pixels in an image. Finally, we refine the saliency map by taking both the textural and structural information into consideration simultaneously. Experiments on publicly available data sets show that our proposed approach achieves competitive results against the state-of-the-art methods.
AB - In the recent research of saliency detection, many graph-based algorithms are applied, which use the border of an image as a background query. This frequently leads to undesired errors and retrieval outputs when the boundaries of the salient objects concerned touch, or connect with, the image's border. In this paper, we propose a novel bottom-up saliency-detection algorithm to tackle and overcome the above issue. First, we utilize object proposals to collect the background seeds reliably. Then, the Extended Random Walk algorithm is adopted to propagate the prior background labels to the rest of the pixels in an image. Finally, we refine the saliency map by taking both the textural and structural information into consideration simultaneously. Experiments on publicly available data sets show that our proposed approach achieves competitive results against the state-of-the-art methods.
UR - http://www.scopus.com/inward/record.url?scp=85056608757&partnerID=8YFLogxK
U2 - 10.23919/APSIPA.2018.8659677
DO - 10.23919/APSIPA.2018.8659677
M3 - Conference article published in proceeding or book
AN - SCOPUS:85056608757
T3 - 2018 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2018 - Proceedings
SP - 1100
EP - 1105
BT - 2018 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2018 - Proceedings
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 10th Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2018
Y2 - 12 November 2018 through 15 November 2018
ER -