Please use this identifier to cite or link to this item:
Title: How important is location information in saliency detection of natural images
Authors: Ren, T
Liu, Y 
Ju, R
Wu, G
Keywords: Location information
Patch representation
Saliency detection
Saliency propagation
Issue Date: 2016
Publisher: Springer
Source: Multimedia tools and applications, 2016, v. 75, no. 5, p. 2543-2564 How to cite?
Journal: Multimedia tools and applications 
Abstract: Location information, i.e., the position of content in image plane, is considered as an important supplement in saliency detection. The effect of location information is usually evaluated by integrating it with the selected saliency detection methods and measuring the improvement, which is highly influenced by the selection of saliency methods. In this paper, we provide direct and quantitative analysis of the importance of location information for saliency detection in natural images. We firstly analyze the relationship between content location and saliency distribution on four public image datasets, and validate the distribution by simply treating location based Gaussian distribution as saliency map. To further validate the effectiveness of location information, we propose a location based saliency detection approach, which completely initializes saliency maps with location information and propagate saliency among patches based on color similarity, and discuss the robustness of location information’s effect. The experimental results show that location information plays a positive role in saliency detection, and the proposed method can outperform most state-of-the-art saliency detection methods and handle natural images with different object positions and multiple salient objects.
ISSN: 1380-7501
DOI: 10.1007/s11042-015-2875-z
Appears in Collections:Journal/Magazine Article

View full-text via PolyU eLinks SFX Query
Show full item record


Last Week
Last month
Citations as of Jun 17, 2017

Page view(s)

Last Week
Last month
Checked on Jun 18, 2017

Google ScholarTM



Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.