Journal of Software, Vol 6, No 9 (2011), 1705-1712, Sep 2011
doi:10.4304/jsw.6.9.1705-1712

A Hierarchical Computational Model of Selective Visual Attention

Qiaorong Zhang, Huimin Xiao, Haibo Liu

Abstract


Computational model of visual attention has got more and more attention in machine vision and image processing. A hierarchical computational model for selective visual attention is proposed in this paper. This model simulates the attention mechanism from far (coarse) to near (fine) of human visual system. Firstly, the input image is analyzed at the coarsest resolution and visual saliency of each part is computed at this level. Regions of attention are selected according to the saliency. Then the sub-regions of the selected region compete for attention at a finer resolution. This process is done iteratively until every salient region and its sub-regions have been processed at different levels respectively. The proposed model has been tested on many natural images. Experiment results show that the proposed model is valid and the attention results are consistent with human visual system.


Keywords


visual attention; image processing; visual saliency; saliency map;hierarchical selection

References


[1] Itti L, Kouch C, and Niebur E, “A model of saliency-based visual attention for rapid scene analysis,” IEEE Transactions on Pattern Analysis and Machine Intelligence, USA, vol. 20, pp. 1254-1259, November 1998.
http://dx.doi.org/10.1109/34.730558

[2] Itti L, Kouch C, “Computational modeling of visual attention,” Nature Reviews Neuroscience, USA, vol. 2, pp.194-230, March 2001.
http://dx.doi.org/10.1038/35058500
PMid:11256080

[3] Itti L, Kouch C, “Feature combination strategies for saliency-based visual attention systems,” Journal of Electronic Imaging, vol. 10, pp.161-169, January 2003.
http://dx.doi.org/10.1117/1.1333677

[4] Dirk Walther, “Interactions of visual attention and object recognition: computational modeling, algorithms, and psychophysics,” PhD thesis, California Institute of Technology, 2006.

[5] Dirk Walther, Christof Koch, “Modeling attention to salient proto-objects,” Neural Networks, USA, vol. 19, pp.1395-1407, 2006.
http://dx.doi.org/10.1016/j.neunet.2006.10.001
PMid:17098563

[6] Yufei Ma, Hongjiang Zhang, “Contrast-based Image Attention Analysis by Using Fuzzy Growing,” Proceedings of the 11th ACM International Conference on Multimedia, March 2003, pp. 374-381.
http://dx.doi.org/10.1145/957013.957094

[7] Zhang Peng, Wang Runsheng, “Detectiong salient regions based on location shift and extent trace,” Journal of Softwarer, China, vol. 15, pp. 891-898, June 2004.

[8] Xiaodi Hou, Liqing Zhang, “Saliency Detection: A Spectral Residual Approach,” IEEE Conference on Computer Vision and Pattern Recognition, June 2007, pp.1-8.
http://dx.doi.org/10.1109/CVPR.2007.383267

[9] Qiaorong Zhang, Guochang Gu, Huimin Xiao, “Image segmentation based on visual attention mechanism,” Journal of Multimedia, Finland, vol. 4, pp. 363-370, December, 2009.

[10] Zheshen Wang, Baoxin Li, “A Two-Stage Approach to Saliency Detection in Images,” IEEE ICASSP 2008, April 2008, pp. 965-968

[11] Yaoru Sun, Robert Fisher, “Object-based Visual Attention for Computer Vision,” Artificial Intelligence, USA, vol. 146, pp. 77-123, January 2003.
http://dx.doi.org/10.1016/S0004-3702(02)00399-5

[12] Yaoru Sun, Robert Fisher, Fang Wang and Herman Martins Gomes, “A Computer Vision Model for Visual-Object-Based Attention and Eye Movements,” Computer Vision and Image Understanding, vol. 112, pp. 126-142, February 2008.
http://dx.doi.org/10.1016/j.cviu.2008.01.005

[13] Yaoru Sun, “Hierarchical object-based visual attention for machine vision,” PhD thesis, University of Edinburgh, 2003.

[14] Qiaorong Zhang, Yafeng Zheng, “An improved computational approach for salient region detection,” Journal of Computers, Finland, in press.

[15] Xuelei Ni, and Xiaoming Huo, “Statistical Interpretation of the Importance of Phase Information in Signal and Image Reconstruction,” Elsevier Science, June 2002.

[16] Peter J. Bex, and Walter Makous, “Spatial frequency, phase, and the contrast of natural images,” Journal of Optical Society, American, vol. 19, pp. 1096-1106, June 2002.
http://dx.doi.org/10.1364/JOSAA.19.001096

[17] Yiqun Hu_, Xing Xie, and Wei-Ying Ma, “Salient Region Detection Using Weighted Feature Maps Based on the Human Visual Attention Model”, LNCS 3332, pp. 993-1000, 2004.


Full Text: PDF


Journal of Software (JSW, ISSN 1796-217X)

Copyright @ 2006-2012 by ACADEMY PUBLISHER – All rights reserved.