An Information Theoretic Model of Saliency and Visual Search
- 1.2k Downloads
In this paper, a proposal which quantifies visual saliency based on an information theoretic definition is evaluated with respect to visual psychophysics paradigms. Analysis reveals that the proposal explains a broad range of results from classic visual search tasks, including many for which only specialized models have had success. As a whole, the results provide strong behavioral support for a model of visual saliency based on information, supplementing earlier work revealing the efficacy of the approach in predicting primate fixation data.
KeywordsAttention Visual Search Saliency Information Theory Fixation Entropy
Unable to display preview. Download preview PDF.
- 1.Bruce, N., Tsotsos, J.K.: Saliency Based on Information Maximization. Advances in Neural Information Processing Systems 18, 155–162 (2006)Google Scholar
- 5.Itti, L., Baldi, P.: Bayesian Surprise Attracts Human Attention. Advances in Neural Information Processing Systems 18, 547–554 (2006)Google Scholar
- 8.Wolfe, J.M.: What Can 1,000,000 Trials Tell Us About Visual Search? Psychological Science 9(1) (1998)Google Scholar
- 12.Tombu, M.N., Tsotsos, J.K.: Attentional inhibitory surrounds in orentation space. Journal of Vision 5(8), 1013, 1013a (2005)Google Scholar
- 14.Rosenholtz, R., Nagy, A.L., Bell, A.R.: The effect of background color on asymmetries in color search. Journal of Vision 4(3), Article 9, 224–240 (2004)Google Scholar