Visual Saliency Detection Based on Deredundancy and Global Contrast

Abstract:

A new method for saliency detection is presented. Based on the sparse coding model, we propose a power spectral filter to eliminate the second-order residual correlation, which suppress the global repeated items effectively. In addition, aim to modeling the mechanism of the human retina prior response to high-contrast stimuli, the effect of color context is considered. Experimental result indicates that our method has high-quality detection performance with respect to the ability not only to highlight the salient objects in complex environment but also to pop up them uniformly.

• Periodical: Applied Mechanics and Materials (Volumes 246-247)
• Pages: 208-212
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.246-247.208
• Online since: December 2012
• Authors: Huan Shen, Xiao Dong Miao, Yun Sheng Tan
• Keywords: Image Processing, Machine Vision, Sparse Coding, Visual Attention

References

[1] T. Alexander, IEEE Trans. Pattern Anal. Mach. Intel. Vol. 33, (2011), p.2131.

[2] L. Itti, C. Koch, and E. Niebur, IEEE Trans. Pattern Anal. Mach. Intel. Vol. 20, (1998), p.1254.

[3] J. Harel, C. Koch and P. Perona, Adv. Neural Inf. Process Syst. Vol. 19, (2007), p.545.

[4] N. D. B. Bruce and J. K. Tsotsos, J. Vision. Vol. 9, (2009), p.1.

[5] W. E. Vinje and J. L. Gallant, Science. Vol. 287, (2000), p.1273.

[6] L. Chen, Vis cogn. Vol. 12, (2005), p.553.

[7] X. Hou and L. Zhang, In Proceedings of IEEE Conference on CVPR. 2007, p.1.

[8] C. Guo and L. Zhang. IEEE Trans. Image Process. Vol. 19, (2010), p.185.

[9] Hyvärinen, P. O. Hoyer, Mika Inki, Neural Comput. Vol. 13, (2001), p.1527.

[10] G. M. Johnson and M. D. Fairchild, Color Res and Appl. Vol. 28, (2003), p.425.