A Study on Image Representation Method Based on Biological Visual Mechanism

Abstract:

Image representation is a key issue among many image processing tasks. By considering the problems faced by current general image representation methods, such as excessive computing amount, sensitivity to noise, lack of self-adaptability etc, a novel image representation method based on biologic visual mechanisms is proposed in this paper. Through simulating the primary visual cortex to realize the sparse representation of outside image it also introduced the synchronization mechanism to make it more accordant with visual system. Finally the presented method was verified by applying it to compress natural images and digital literature images respectively. The result showed that this new representation method is better than the general sparse representation method on both aspects of compression ratio and noise sensitivity.

• Periodical: Applied Mechanics and Materials (Volumes 249-250)
• Pages: 1283-1288
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.249-250.1283
• Online since: December 2012
• Authors: Li Shi, Xiao Ke Niu, Zhi Zhong Wang, Hui Ge Shi
• Keywords: Biological Visual Cortex, Image Representation, Sparse Response, Synchronization Oscillation

References

[1] Xiao Q, Ding X H, Wang Sh J, et al. Image denois-ing based on adaptive over-complete sparse representation［J］. Chinese Journal of Scientific Instrument. 2009. 30(9): 1886-1890.

[2] Gabriel P. A Review of Adaptive Image Representations[J]. IEEE Journal Of Selected Topics In Signal Processing. 2011. 5(5): 896-911.

[3] Zhang Y W, Liu Y L. Research of static image compression algorithm based on JPEG standard. Electronic Design Engineering. 2010. 18(2): 77-80.

[4] Jiao L Ch, Tan Sh. Development and Prospect of Image Multiscale Geometric Analysis. Acta Electronica Sinica. 2003. 31(12): 1975-(1981).

[5] S. Mallat, Z. Zhang. Matching pursuits with time-frequency dictionaries[J]. IEEE Transaction on Signal Process. 1993. 41(12): 3397-3415.

DOI: 10.1109/78.258082

[6] Aharon M, Elad M, Bruckstein A M. The K-SVD: An algorithm for designing of overcomplete dictionaries for sparse representation[J]. IEEE Transactions on Signal Processing. 2006. 54(11): 4311-4322.

DOI: 10.1109/tsp.2006.881199

[7] Gutierrez J, Ferri F J, Malo J. Regularization Operators for Natural Images Based on Nonlinear Perception Models[J]. Image Proeessing. 2006. 15(1): 189-200.

DOI: 10.1109/tip.2005.860345

[8] Wang Zh, Huang Y P, Luo X Y, et al. Learning Topographic Representations of Nature Images with Pairwise Cumulant [J]. Neural Process Lett. 2011. 34: 155–175.

DOI: 10.1007/s11063-011-9189-6

[9] Eckhom R. A Neural Network for Future Linking via Synehronous activity: Results from Cat Visual Cortex and from Simulations [J]. In Models of Brain Function. 1989: 255-272.