Publication Type

Conference Proceeding Article

Version

acceptedVersion

Publication Date

1-2013

Abstract

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.

Keywords

image abstraction; object of interest segmentation; salient object detection; visual attention

Discipline

Graphics and Human Computer Interfaces

Research Areas

Data Science and Engineering

Publication

Proceedings of the 14th IEEE International Conference on Computer Vision, ICCV 2013, Sydney, December 1-8

First Page

1529

Last Page

1536

ISBN

9781479928392

Identifier

10.1109/ICCV.2013.193

Publisher

Institute of Electrical and Electronics Engineers Inc.

City or Country

Sydney, Australia

Additional URL

https://doi.org/10.1109/ICCV.2013.193

Download

Share

COinS