articleDec 1, 2013GREEN OA

Efficient Salient Region Detection with Soft Image Abstraction

Oxford Brookes University

Indexed incrossref

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…

Citation impact

575
total citations
FWCI
61.03
Percentile
100%
References
64
Citations per year

Authors

6

Topics & keywords

Keywords
  • Salient
  • Artificial intelligence
  • Computer science
  • Pixel
  • Abstraction
  • Pattern recognition (psychology)
  • Image (mathematics)
  • Similarity (geometry)
No related works found for this paper.

Funding