Efficient salient region detection with soft image abstraction

Detecting visually salient regions in images is one of the fundamental problems in computer vision. We propose a novel method to decompose an image into large scale perceptually homogeneous elements for efficient salient region detection, using a soft image abstraction representation. By considering...

Full description

Saved in:
Bibliographic Details
Main Authors: CHENG, Ming-Ming, WARRELL, Jonathan, LIN, Wen-yan, ZHENG, Shuai, VINEET, Vibhav, CROOK, Nigel
Format: text
Language:English
Published: Institutional Knowledge at Singapore Management University 2013
Subjects:
Online Access:https://ink.library.smu.edu.sg/sis_research/4804
https://ink.library.smu.edu.sg/context/sis_research/article/5807/viewcontent/Cheng_ICCV2013.pdf
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Singapore Management University
Language: English
id sg-smu-ink.sis_research-5807
record_format dspace
spelling sg-smu-ink.sis_research-58072020-01-16T10:05:24Z Efficient salient region detection with soft image abstraction CHENG, Ming-Ming WARRELL, Jonathan LIN, Wen-yan ZHENG, Shuai VINEET, Vibhav CROOK, Nigel Detecting visually salient regions in images is one of the fundamental problems in computer vision. We propose a novel method to decompose an image into large scale perceptually homogeneous elements for efficient salient region detection, using a soft image abstraction representation. By considering both appearance similarity and spatial distribution of image pixels, the proposed representation abstracts out unnecessary image details, allowing the assignment of comparable saliency values across similar regions, and producing perceptually accurate salient region detection. We evaluate our salient region detection approach on the largest publicly available dataset with pixel accurate annotations. The experimental results show that the proposed method outperforms 18 alternate methods, reducing the mean absolute error by 25.2% compared to the previous best result, while being computationally more efficient. 2013-01-08T08:00:00Z text application/pdf https://ink.library.smu.edu.sg/sis_research/4804 info:doi/10.1109/ICCV.2013.193 https://ink.library.smu.edu.sg/context/sis_research/article/5807/viewcontent/Cheng_ICCV2013.pdf http://creativecommons.org/licenses/by-nc-nd/4.0/ Research Collection School Of Computing and Information Systems eng Institutional Knowledge at Singapore Management University image abstraction; object of interest segmentation; salient object detection; visual attention Graphics and Human Computer Interfaces
institution Singapore Management University
building SMU Libraries
continent Asia
country Singapore
Singapore
content_provider SMU Libraries
collection InK@SMU
language English
topic image abstraction; object of interest segmentation; salient object detection; visual attention
Graphics and Human Computer Interfaces
spellingShingle image abstraction; object of interest segmentation; salient object detection; visual attention
Graphics and Human Computer Interfaces
CHENG, Ming-Ming
WARRELL, Jonathan
LIN, Wen-yan
ZHENG, Shuai
VINEET, Vibhav
CROOK, Nigel
Efficient salient region detection with soft image abstraction
description Detecting visually salient regions in images is one of the fundamental problems in computer vision. We propose a novel method to decompose an image into large scale perceptually homogeneous elements for efficient salient region detection, using a soft image abstraction representation. By considering both appearance similarity and spatial distribution of image pixels, the proposed representation abstracts out unnecessary image details, allowing the assignment of comparable saliency values across similar regions, and producing perceptually accurate salient region detection. We evaluate our salient region detection approach on the largest publicly available dataset with pixel accurate annotations. The experimental results show that the proposed method outperforms 18 alternate methods, reducing the mean absolute error by 25.2% compared to the previous best result, while being computationally more efficient.
format text
author CHENG, Ming-Ming
WARRELL, Jonathan
LIN, Wen-yan
ZHENG, Shuai
VINEET, Vibhav
CROOK, Nigel
author_facet CHENG, Ming-Ming
WARRELL, Jonathan
LIN, Wen-yan
ZHENG, Shuai
VINEET, Vibhav
CROOK, Nigel
author_sort CHENG, Ming-Ming
title Efficient salient region detection with soft image abstraction
title_short Efficient salient region detection with soft image abstraction
title_full Efficient salient region detection with soft image abstraction
title_fullStr Efficient salient region detection with soft image abstraction
title_full_unstemmed Efficient salient region detection with soft image abstraction
title_sort efficient salient region detection with soft image abstraction
publisher Institutional Knowledge at Singapore Management University
publishDate 2013
url https://ink.library.smu.edu.sg/sis_research/4804
https://ink.library.smu.edu.sg/context/sis_research/article/5807/viewcontent/Cheng_ICCV2013.pdf
_version_ 1770575036469477376