Conference Paper

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 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.

Attached files


Cheng Ming-Ming
Warrell, Jonathan
Lin Wen-Yan
Zheng Shuai
Vineet, Vibhav
Crook, Nigel

Oxford Brookes departments

School of Engineering, Computing and Mathematics


Year of publication: 2014
Date of RADAR deposit: 2019-08-16

Creative Commons License This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License

Related resources

This RADAR resource is the Accepted Manuscript of Efficient Salient Region Detection with Soft Image Abstraction


  • Owner: Joseph Ripp
  • Collection: Outputs
  • Version: 1 (show all)
  • Status: Live
  • Views (since Sept 2022): 343