2012 | OriginalPaper | Chapter
A Modified GBVS Method with Entropy for Extracting Bottom-Up Attention Information
Authors : Jiuyu Sun, Ruofan Chen, Jun He
Published in: Advances in Computer, Communication, Control and Automation
Publisher: Springer Berlin Heidelberg
Activate our intelligent search to find suitable subject content or patents.
Select sections of text to find matching patents with Artificial Intelligence. powered by
Select sections of text to find additional relevant content using AI-assisted search. powered by
A bottom-up visual attention extraction method is presented in the paper. Based on experiments, we have found that the original Graph-Based Visual Saliency (GBVS) method proposed by Itti had not taken signal complexity into consideration, which just can be measured with entropy. Thus, a modified attention model which combines GBVS and entropy measurement has been provided in the paper. What’s more, some experiments are also given which indicates the effect on extracting bottom-up attention information with the modified model.