Skip navigation

A prior regularized multi-layer graph ranking model for image saliency computation

A prior regularized multi-layer graph ranking model for image saliency computation

Xiao, Yun, Jiang, Bo, Tu, Zhengzheng, Ma, Jixin and Tang, Jin ORCID: 0000-0002-2194-0179 (2018) A prior regularized multi-layer graph ranking model for image saliency computation. Neurocomputing, 315 (13). pp. 234-245. ISSN 0925-2312 (doi:https://doi.org/10.1016/j.neucom.2018.06.072)

[img] PDF (Published version)
24364 MA_Regularized_Multi-layer_Ranking_Model_Image_Saliency_Computation_(Pub)_2018.pdf - Published Version
Restricted to Registered users only

Download (3MB) | Request a copy

Abstract

Bottom-up saliency detection has been widely studied in many applications, such as image retrieval, object recognition, image compression and so on. Saliency detection via manifold ranking (MR) can identify the most salient and important area from an image efficiently. One limitation of the MR model is that it fails to consider the prior information in its ranking process. To overcome this limitation, we propose a prior regularized multi-layer graph ranking model (RegMR), which uses the prior calculating by boundary connectivity. We employ the foreground possibility in the first stage and background possibility in the second stage based on a multi-layer graph. We compare our model with fifteen state-of-the-art methods. Experiments show that our model performs well than all other methods on four public databases on PR-curves, F-measure and so on.

Item Type: Article
Uncontrolled Keywords: graph ranking, boundary connectivity, background possibility, foreground possibility, multiple layer
Subjects: Q Science > QA Mathematics > QA75 Electronic computers. Computer science
Faculty / Department / Research Group: Faculty of Architecture, Computing & Humanities
Faculty of Architecture, Computing & Humanities > Centre for Computer & Computational Science
Faculty of Architecture, Computing & Humanities > Department of Computing & Information Systems
Last Modified: 13 Aug 2019 11:35
Selected for GREAT 2016: None
Selected for GREAT 2017: None
Selected for GREAT 2018: None
Selected for GREAT 2019: GREAT 3
URI: http://gala.gre.ac.uk/id/eprint/24364

Actions (login required)

View Item View Item

Downloads

Downloads per month over past year

View more statistics