Biologically Inspired Saliency Map Model for Bottom-up Visual Attention
In this paper, we propose a new saliency map model to find a selective attention region in a static color image for human-like fast scene analysis. We consider the roles of cells in our visual receptor for edge detection and cone opponency, and also reflect the roles of the lateral geniculate nucleus to find a symmetrical property of an interesting object such as shape and pattern. Also, independent component analysis (ICA) is used to find a filter that can generate a salient region from feature maps constructed by edge, color opponency and symmetry information, which models the role of redundancy reduction in the visual cortex. Computer experimental results show that the proposed model successfully generates the plausible sequence of salient region.
KeywordsVisual Cortex Independent Component Analysis Independent Component Analysis Lateral Geniculate Nucleus Salient Region
Unable to display preview. Download preview PDF.
- 2.Yagi, T., Asano, N., Makita, S., Uchikawa, Y.: Active vision inspired by mammalian fixation mechanism. Intelligent Robots and Systems (1995) 39–47Google Scholar
- 4.Barlow, H. B., Tolhust, D. J.: Why do you have edge detectors? Optical society of America Technical Digest. 23 (1992) 172Google Scholar
- 7.Wachtler, T., Lee, T. W., Sejnowski, T. J.: Chromatic structure of natural scenes. J. Opt. Soc. Am. A, Vol. 18 (2001) No. 1Google Scholar
- 8.Bruce Goldstein E.: Sensation and Perception. 4th edn. An international Thomson publishing company, USA (1995)Google Scholar
- 9.Majani, E., Erlanson, R., Abu-Mostafa, Y.: The Eye. Academic, New York (1984)Google Scholar
- 10.Kuffler, S. W., Nicholls, J. G., Martin, J. G.: From Neuron to Brain. Sinauer Associates, Sunderland, U.K (1984)Google Scholar
- 11.Gonzalez, R. G., Woods, R. E.: Digital Image Processing. Addison-Wesley Publishing Company, USA (1993)Google Scholar
- 12.Lee, T. W.: Independent Component Analysis-theory and application. Kluwer academic publisher, (1998)Google Scholar
- 13.Seo, K. S., Park, C.J., Cho, S.H., Choi, H. M.: Context-Free Marker-Controlled Watershed Transform for Efficient Multi-Object Detection and Segmentation. IEICE TRANS. Vol. E84-A. Jun. (2001) No. 6Google Scholar