Indexed by:
期刊论文
First Author:
Gao, Zhenguo
Correspondence Author:
Ayoub, N (reprint author), Dalian Univ Technol, Sch Comp Sci & Technol, Dalian 116024, Peoples R China.
Co-author:
Ayoub, Naeem,Chen, Danjie,Chen, Bingcai,Lu, Zhimao
Date of Publication:
2018-01-01
Journal:
IEEE ACCESS
Included Journals:
SCIE
Document Type:
J
Volume:
6
Page Number:
71422-71434
ISSN No.:
2169-3536
Key Words:
Saliency detection; image segmentation; artificial intelligence;
absorption Markov model; eye fixation prediction; guided filter
Abstract:
In this paper, we propose a saliency detection method (SAMM) by using the surroundedness and absorption Markov model. First, the approximate area of the salient object is predicted by the surroundedness to the eye fixation point prediction. Second, a simple linear iterative clustering algorithm is applied to the original image to calculate superpixels, and a two-ring image graph model is formed. We calculate two initial saliency maps S-1 and S-2. Prior map S-1 is calculated by applying the absorption Markov chain, as the superpixel-based region of the two boundaries farthest from the predicted salient object is taken as the background region, while map S-2 is calculated by using the absorption Markov chain to detect the superpixels in the approximate region of the salient object as a foreground region. The final saliency map is obtained by combining S-1 and S-2. Finally, a guided filter is used to reduce the background noise from the saliency map. For the evaluation, experiments are performed on six publicly available test datasets (MSRA, ECSSD, Imgsal, DUT-OMRON, PASCAL-S, and MSRA10k), and the results are compared against 10 state-of-theart saliency detection algorithms. Our proposed saliency detection algorithm (SAMM) performs better with higher precision recall, AUC, F-measure, and minimum mean absolute error values.
Translation or Not:
no
