|
| This Article | ||
| ||
| Share | ||
| Bibliographic References | ||
| Add to: | ||
 Digg  Furl  Spurl  Blink  Simpy  Google  Del.icio.us  Y!MyWeb | ||
| Search | ||
| ||
2010 Sixth International Conference on Intelligent Information Hiding and Multimedia Signal Processing
A Saliency Map Model Based on the Principle of Maximum Information Gain
Darmstadt, Germany
October 15-October 17
ISBN: 978-0-7695-4222-5
| ASCII Text | x | ||
| Takashi Toriu, Shigeyoshi Nakajima, Hiromitsu Hama, "A Saliency Map Model Based on the Principle of Maximum Information Gain," Intelligent Information Hiding and Multimedia Signal Processing, International Conference on, pp. 668-671, 2010 Sixth International Conference on Intelligent Information Hiding and Multimedia Signal Processing, 2010. | |||
| BibTex | x | ||
| @article{ 10.1109/IIHMSP.2010.169, author = {Takashi Toriu and Shigeyoshi Nakajima and Hiromitsu Hama}, title = {A Saliency Map Model Based on the Principle of Maximum Information Gain}, journal ={Intelligent Information Hiding and Multimedia Signal Processing, International Conference on}, volume = {0}, year = {2010}, isbn = {978-0-7695-4222-5}, pages = {668-671}, doi = {http://doi.ieeecomputersociety.org/10.1109/IIHMSP.2010.169}, publisher = {IEEE Computer Society}, address = {Los Alamitos, CA, USA}, } | |||
| RefWorks Procite/RefMan/Endnote | x | ||
| TY - CONF JO - Intelligent Information Hiding and Multimedia Signal Processing, International Conference on TI - A Saliency Map Model Based on the Principle of Maximum Information Gain SN - 978-0-7695-4222-5 SP668 EP671 A1 - Takashi Toriu, A1 - Shigeyoshi Nakajima, A1 - Hiromitsu Hama, PY - 2010 KW - Saliency map KW - visual attention KW - maximum information gain KW - entropy VL - 0 JA - Intelligent Information Hiding and Multimedia Signal Processing, International Conference on ER - | |||
Humans do not process the entire area of an input visual image uniformly, but usually focus their visual attention on a limited area. But where does a human focus that attention? Psychological phenomena indicate that attention is attracted to features that differ from its surroundings or the one that are unfamiliar. On the bases of this we developed a saliency map model, which predicts where attention is attracted, based on two-step principal component analysis. In this paper, we reformulate this model based by the principle of maximizing information gain. On the basis of this theoretical foundation, we further investigate how this model could be modified in a situation where human must find something. We show experimental results and discuss future problems.
Index Terms:
Saliency map, visual attention, maximum information gain, entropy
Citation:
Takashi Toriu, Shigeyoshi Nakajima, Hiromitsu Hama, "A Saliency Map Model Based on the Principle of Maximum Information Gain," iih-msp, pp.668-671, 2010 Sixth International Conference on Intelligent Information Hiding and Multimedia Signal Processing, 2010
Usage of this product signifies your acceptance of the Terms of Use.