Saliency Detection: A Spectral Residual Approach
Top Cited Papers
- 1 June 2007
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 10636919,p. 1-8
- https://doi.org/10.1109/cvpr.2007.383267
Abstract
The ability of human visual system to detect visual saliency is extraordinarily fast and reliable. However, computational modeling of this basic intelligent behavior still remains a challenge. This paper presents a simple method for the visual saliency detection. Our model is independent of features, categories, or other forms of prior knowledge of the objects. By analyzing the log-spectrum of an input image, we extract the spectral residual of an image in spectral domain, and propose a fast method to construct the corresponding saliency map in spatial domain. We test this model on both natural pictures and artificial images such as psychological patterns. The result indicate fast and robust saliency detection of our method.Keywords
This publication has 18 references indexed in Scilit:
- Hybrid imagesACM Transactions on Graphics, 2006
- On the spatial statistics of optical flowPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2005
- Modeling global scene factors in attentionJournal of the Optical Society of America A, 2003
- Depth estimation from image structurePublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Natural Image Statistics and Neural RepresentationAnnual Review of Neuroscience, 2001
- Seeing, sensing, and scrutinizingVision Research, 2000
- Origins of scaling in natural imagesVision Research, 1997
- To See or not to See: The Need for Attention to Perceive Changes in ScenesPsychological Science, 1997
- Preemption effects in visual search: Evidence for low-level grouping.Psychological Review, 1995
- The statistics of natural imagesNetwork: Computation in Neural Systems, 1994