Abstract
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.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
Similar content being viewed by others
References
Itti, L., Koch, C.: Computational modeling of visual attention. Nature Reviews of Neuroscience 2(3), 194–230 (2001)
Luo, S.W.: Information processing theory of visual perception. Electronic Industry Press (February 2006)
Treisman, A.M.: A Feature-Integration Theory of Attention. Cognitive Psychology 12, 97–136 (1980)
Itti, L., Koch, C., Niebur, E.: A Model of Saliency-based Visual Attention for Rapid Scene Analysis, The Computation and Neural Systems Program, California Institute of Technology–139-74, Pasadena, CA 91125
Tian, M., Luo, S.W., Huang, Y.P., Zhao, J.L.: Extracting Bottom-Up Attention Information Based on Local Complexity and Early Visual Features. Journal of Computer Research and Development 45(10), 1739–1746 (2008) ISSN 1000-1239/CN 11-1777/TP
Gilles, S.: Robust description and matching of images. University of Oxford, Oxford (1998)
Burt, P.J., Adelson, E.H.: The Laplacian Pyramid as a Compact Image Code. IEEE Transactions On Communications Com-3l(4) (April 1983)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2011 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Sun, J., Chen, R., He, J. (2011). A Modified GBVS Method with Entropy for Extracting Bottom-Up Attention Information. In: Wu, Y. (eds) Advances in Computer, Communication, Control and Automation. Lecture Notes in Electrical Engineering, vol 121. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-25541-0_96
Download citation
DOI: https://doi.org/10.1007/978-3-642-25541-0_96
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-25540-3
Online ISBN: 978-3-642-25541-0
eBook Packages: EngineeringEngineering (R0)