Region Enhanced Scale-Invariant Saliency Detection
- 1 July 2006
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 19457871,p. 1477-1480
- https://doi.org/10.1109/icme.2006.262821
Abstract
Saliency measures the low-level stimuli to human vision, and serves as an alternative to semantic image understanding. This paper presents a region enhanced scale-invariant saliency detection method. Our method constructs a scale-invariant saliency map from an image, segments the image into regions, and enhances the saliency map with the region information. Compared with previous methods, our method has advantages in providing robust scale-invariant saliency, giving meaningful region information for applications, and eliminating misleading high-contrast edgesKeywords
This publication has 13 references indexed in Scilit:
- Robust subspace analysis for detecting visual attention regions in imagesPublished by Association for Computing Machinery (ACM) ,2005
- Automatic image retargetingPublished by Association for Computing Machinery (ACM) ,2005
- Effective browsing of web image search resultsPublished by Association for Computing Machinery (ACM) ,2004
- Automatic thumbnail cropping and its effectivenessPublished by Association for Computing Machinery (ACM) ,2003
- A visual attention model for adapting images on small displaysMultimedia Systems, 2003
- Salient region detection and tracking in videoPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2003
- A user attention model for video summarizationPublished by Association for Computing Machinery (ACM) ,2002
- Computational modelling of visual attentionNature Reviews Neuroscience, 2001
- Salience from feature contrast: additivity across dimensionsVision Research, 2000
- Mean shift analysis and applicationsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1999