A Synthetic Fusion Rule for Salient Region Detection under the Framework of DS-Evidence Theory
Saliency detection is one of the most valuable research topics in computer vision. It focuses on the detection of the most significant objects/regions in images and reduces the computational time cost of getting the desired information from salient regions. Local saliency detection or common pattern...
Main Authors: | , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2018-05-01
|
Series: | Symmetry |
Subjects: | |
Online Access: | http://www.mdpi.com/2073-8994/10/6/183 |
_version_ | 1811306295645437952 |
---|---|
author | Naeem Ayoub Zhenguo Gao Bingcai Chen Muwei Jian |
author_facet | Naeem Ayoub Zhenguo Gao Bingcai Chen Muwei Jian |
author_sort | Naeem Ayoub |
collection | DOAJ |
description | Saliency detection is one of the most valuable research topics in computer vision. It focuses on the detection of the most significant objects/regions in images and reduces the computational time cost of getting the desired information from salient regions. Local saliency detection or common pattern discovery schemes were actively used by the researchers to overcome the saliency detection problems. In this paper, we propose a bottom-up saliency fusion method by taking into consideration the importance of the DS-Evidence (Dempster–Shafer (DS)) theory. Firstly, we calculate saliency maps from different algorithms based on the pixels-level, patches-level and region-level methods. Secondly, we fuse the pixels based on the foreground and background information under the framework of DS-Evidence theory (evidence theory allows one to combine evidence from different sources and arrive at a degree of belief that takes into account all the available evidence). The development inclination of image saliency detection through DS-Evidence theory gives us better results for saliency prediction. Experiments are conducted on the publicly available four different datasets (MSRA, ECSSD, DUT-OMRON and PASCAL-S). Our saliency detection method performs well and shows prominent results as compared to the state-of-the-art algorithms. |
first_indexed | 2024-04-13T08:42:58Z |
format | Article |
id | doaj.art-16a74d02e4334a03b072ad7a5388a6c2 |
institution | Directory Open Access Journal |
issn | 2073-8994 |
language | English |
last_indexed | 2024-04-13T08:42:58Z |
publishDate | 2018-05-01 |
publisher | MDPI AG |
record_format | Article |
series | Symmetry |
spelling | doaj.art-16a74d02e4334a03b072ad7a5388a6c22022-12-22T02:53:50ZengMDPI AGSymmetry2073-89942018-05-0110618310.3390/sym10060183sym10060183A Synthetic Fusion Rule for Salient Region Detection under the Framework of DS-Evidence TheoryNaeem Ayoub0Zhenguo Gao1Bingcai Chen2Muwei Jian3School of Computer Science and Technology, Dalian University of Technology, Dalian 116024, ChinaSchool of Computer Science and Technology, Dalian University of Technology, Dalian 116024, ChinaSchool of Computer Science and Technology, Dalian University of Technology, Dalian 116024, ChinaSchool of Computer Science and Technology, Shandong University of Finance and Economics, Jinan 250100, ChinaSaliency detection is one of the most valuable research topics in computer vision. It focuses on the detection of the most significant objects/regions in images and reduces the computational time cost of getting the desired information from salient regions. Local saliency detection or common pattern discovery schemes were actively used by the researchers to overcome the saliency detection problems. In this paper, we propose a bottom-up saliency fusion method by taking into consideration the importance of the DS-Evidence (Dempster–Shafer (DS)) theory. Firstly, we calculate saliency maps from different algorithms based on the pixels-level, patches-level and region-level methods. Secondly, we fuse the pixels based on the foreground and background information under the framework of DS-Evidence theory (evidence theory allows one to combine evidence from different sources and arrive at a degree of belief that takes into account all the available evidence). The development inclination of image saliency detection through DS-Evidence theory gives us better results for saliency prediction. Experiments are conducted on the publicly available four different datasets (MSRA, ECSSD, DUT-OMRON and PASCAL-S). Our saliency detection method performs well and shows prominent results as compared to the state-of-the-art algorithms.http://www.mdpi.com/2073-8994/10/6/183image processingimage analysisobject detectionsaliency detectionDS-Evidence theorysaliency fusion |
spellingShingle | Naeem Ayoub Zhenguo Gao Bingcai Chen Muwei Jian A Synthetic Fusion Rule for Salient Region Detection under the Framework of DS-Evidence Theory Symmetry image processing image analysis object detection saliency detection DS-Evidence theory saliency fusion |
title | A Synthetic Fusion Rule for Salient Region Detection under the Framework of DS-Evidence Theory |
title_full | A Synthetic Fusion Rule for Salient Region Detection under the Framework of DS-Evidence Theory |
title_fullStr | A Synthetic Fusion Rule for Salient Region Detection under the Framework of DS-Evidence Theory |
title_full_unstemmed | A Synthetic Fusion Rule for Salient Region Detection under the Framework of DS-Evidence Theory |
title_short | A Synthetic Fusion Rule for Salient Region Detection under the Framework of DS-Evidence Theory |
title_sort | synthetic fusion rule for salient region detection under the framework of ds evidence theory |
topic | image processing image analysis object detection saliency detection DS-Evidence theory saliency fusion |
url | http://www.mdpi.com/2073-8994/10/6/183 |
work_keys_str_mv | AT naeemayoub asyntheticfusionruleforsalientregiondetectionundertheframeworkofdsevidencetheory AT zhenguogao asyntheticfusionruleforsalientregiondetectionundertheframeworkofdsevidencetheory AT bingcaichen asyntheticfusionruleforsalientregiondetectionundertheframeworkofdsevidencetheory AT muweijian asyntheticfusionruleforsalientregiondetectionundertheframeworkofdsevidencetheory AT naeemayoub syntheticfusionruleforsalientregiondetectionundertheframeworkofdsevidencetheory AT zhenguogao syntheticfusionruleforsalientregiondetectionundertheframeworkofdsevidencetheory AT bingcaichen syntheticfusionruleforsalientregiondetectionundertheframeworkofdsevidencetheory AT muweijian syntheticfusionruleforsalientregiondetectionundertheframeworkofdsevidencetheory |