Sparse Representation of the Human Vision Information and the Saliency Detection Algorithm

Ju Bo Jin; Yu Xi Liu

doi:10.4028/www.scientific.net/AMM.513-517.3349

Paper Titles

A Design of Direct Sequence Spread Spectrum Module with Variable Bandwidth Based on FPGA
p.3332

Design and Implementation of Remote Intelligent Control System Based on Cortex-M3
p.3336

Electromagnetic Response for Horizontal Electric Dipole Source Considering Conduct & Displacement Current
p.3340

Research on Combined Environmental Stress Test for Hybrid Integrated DC/DC Converter
p.3345

Sparse Representation of the Human Vision Information and the Saliency Detection Algorithm
p.3349

Image Segmentation Algorithm Research for Sport Graphics Based on Artificial Life
p.3354

A Novel Approach Based on Multi-Layer Background Subtraction and Seed Region Growing for Sport Graphics Segmentation
p.3358

Enhancement Algorithm of Color Fog Image Based on the Adaptive Scale and S-Cosine Curve
p.3362

Regions of Interest Detection Algorithm Based on Improved Visual Attention Model
p.3368

HomeApplied Mechanics and MaterialsApplied Mechanics and Materials Vols. 513-517Sparse Representation of the Human Vision...

Sparse Representation of the Human Vision Information and the Saliency Detection Algorithm

Abstract:

Representation and measurement are two important issues for saliency models. Different with previous works that learnt sparse features from large scale natural statistics, we propose to learn features from short-term statistics of single images. For saliency measurement, we defined basic firing rate (BFR) for each sparse feature, and then we propose to use feature activity rate (FAR) to measure the bottom-up visual saliency. The proposed FAR measure is biological plausible and easy to compute and with satisfied performance. Experiments on human trajectory positioning and psychological patterns demonstrate the effectiveness and robustness of our proposed method.

You might also be interested in these eBooks

View Preview

Info:

Periodical:

Applied Mechanics and Materials (Volumes 513-517)

Pages:

3349-3353

DOI:

https://doi.org/10.4028/www.scientific.net/AMM.513-517.3349

Citation:

Cite this paper

Online since:

February 2014

Authors:

Ju Bo Jin, Yu Xi Liu*

Keywords:

Background Firing Rate, Feature Activation Rate, K-SVD Algorithm, Visual Attention Mechanism

Export:

RIS, BibTeX

Price:

Permissions CCC:

Request Permissions

Permissions PLS:

Request Permissions

Сopyright:

Citation:

* - Corresponding Author

References

[1] A. L. Yarbus. Eye Movements and Vision [M]. New York：Plenum Press. 1967: 123-165.

Google Scholar

[2] D. Vishwanath, E. Kowler. Localization of shapes: Eye movements and perception compared [J]. Vision Research. 2003(43): 1637-1653.

DOI: 10.1016/s0042-6989(03)00168-8

Google Scholar

[3] R.A. Abrams, S. E. Christ. Motion onset captures attention [J]. Psychological Science. 2003, 14(5): 427-432.

DOI: 10.1111/1467-9280.01458

Google Scholar

[4] Itti L，Koch C. Niebur E. A model of saliency—based visual attention for rapid scene analysis[C]．IEEE Trans on Pattern Analysis and Machine Intelligence，1998，20(11)：1254-1259.

DOI: 10.1109/34.730558

Google Scholar

[5] Koch C，Ullman S．Shifts in selective visual attention：towards the underlying neural circuitry[J]．Human Neurobiology，1985，4(4)：219-227.

Google Scholar

[6] Itti L，Koch C．Computational model of visual attention[J]．Nature Reviews Neuroscience, 2001，2(3)：194-230.

Google Scholar

[7] X. Hou and L. Zhang, Dynamic visual attention: searching for coding length increments[C]., in Advances in Neural Information Processing Systems, (NIPS), 2008: 681-688.

Google Scholar

[8] M. Aharon, M. Elad and A. Bruckstein, K-SVD: An Algorithm for Designing Overcomplete Dictionaries for Sparse Representation[C], IEEE Transactions on Image Processing, vol. 54, no. 11, p.4311, 2006: 1-4.

DOI: 10.1109/tsp.2006.881199

Google Scholar

[9] C. Guo, Q. Ma, and L. Zhang, Spatio-temporal saliency detection using phase spectrum of quaternion fourier transform[C], in IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2008: 1-8.

DOI: 10.1109/cvpr.2008.4587715

Google Scholar