Skip to content
Anchorcite

Graph-Based Visual Saliency

Jonathan Harel, Christof Koch, Pietro Perona

The MIT Press eBooks · 2007 · 3,494 citations

doi.org/10.7551/mitpress/7503.003.0073

Abstract

A new bottom-up visual saliency model, Graph-Based Visual Saliency (GBVS), is proposed. It consists of two steps: first forming activation maps on certain feature \nchannels, and then normalizing them in a way which highlights conspicuity and admits combination with other maps. The model is simple, and biologically plausible \ninsofar as it is naturally parallelized. This model powerfully predicts human fixations on 749 variations of 108 natural images, achieving 98% of the ROC area \nof a human-based control, whereas the classical algorithms of Itti & Koch ([2], [3], [4]) achieve only 84%.

Cite this paper

Harel, J., Koch, C., & Perona, P. (2007). Graph-based visual saliency. In The MIT Press eBooks (pp. 545–552). The MIT Press. https://doi.org/10.7551/mitpress/7503.003.0073

Read it with every claim anchored

Add this paper to a project, ask questions of it, and get answers that point to the exact passage.

Start free

Related papers

  1. A model of saliency-based visual attention for rapid scene analysis1998
  2. Statistical parametric maps in functional imaging: A general linear approach1994
  3. Structural absorption by barbule microstructures of super black bird of paradise feathers2017
  4. Receptive fields and functional architecture of monkey striate cortex1968
  5. Theory of edge detection1980

Metadata from OpenAlex (CC0). Citations are generated from the published record.