Visual saliency detection with center shift

This paper proposes a novel method for visual saliency detection based on an universal probabilistic model, which measures the saliency by combining low level features and location prior. We view the task of estimating visual saliency as searching the most conspicuous parts in an image and extract t...

Full description

Saved in:
Bibliographic Details
Published in:Neurocomputing (Amsterdam) 2013-03, Vol.103, p.63-74
Main Authors: Yang, Weibin, Tang, Yuan Yan, Fang, Bin, Shang, Zhaowei, Lin, Yuewei
Format: Article
Language:English
Subjects:
Applied sciences
Artificial intelligence
Center shift
Computer science
control theory
systems
Computer simulation
Estimating
Exact sciences and technology
Human
Human fixation
Image detection
Mathematical models
Multiscale analysis
Pattern recognition. Digital image processing. Computational geometry
Position (location)
Probabilistic model
Salient object
Searching
Visual
Visual saliency
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:This paper proposes a novel method for visual saliency detection based on an universal probabilistic model, which measures the saliency by combining low level features and location prior. We view the task of estimating visual saliency as searching the most conspicuous parts in an image and extract the saliency map by computing the dissimilarity between different regions. We simulate the moving of the center of human visual field, and describe how the center shift process works on visual saliency. Furthermore, multiscale analysis is adopted for improving the robustness of our model. Experimental results on three public image datasets show that the proposed approach outperforms 18 state-of-the-art methods for both salient object detection and human eye fixation prediction.
ISSN:0925-2312
1872-8286
DOI:10.1016/j.neucom.2012.08.029