Image Restoration Based on Pulse Coupled Neural Network

Abstract:

Image is the unity structure and texture, structure reflects to the contours and the boundaries between different regions in the image, and the texture is a reflection of the details within an area in the image, therefore the optimal restoration effect can not be achieved if structure or texture is considered separately during the process of image restoration. In order to solve the problems above, the corresponding solution proposed in this paper is as follows: first, the structural characteristics of the image to be repaired are obtained by using pulse coupled neural network; then both the textural features and the structural features are taken into consideration simultaneously when it comes to the priority of the image restoration as well as the calculation of the optimal sample block. It can be seen from the experimental results that the algorithm described herein can effectively improve the quality of image restoration.

• Periodical: Applied Mechanics and Materials (Volume 741)
• Pages: 368-372
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.741.368
• Online since: March 2015
• Authors: Yong Sheng Xu*, Shu Wen Wang, Tao Wu
• Keywords: Image Restoration, Pulse Coupled Neural Network, Structure, Texture

References

[1] Chan T F and Shen J H. Mathematical Models for Local Non-Texture Restoration. SIAM Journal on APPljed Mathematies, 2002: 1019-1043.

[2] T. F. Chan and J. Shen. Non-texture restoration by curvature-driven diffusions (CCD). J. Visual Comm. Image Rep., 4(12): 436-449, (2001).

[3] A. Criminisi, P. Perez and K. oyama. Region Filling and Object Removal by Exemplar-Based Image Restoration. IEEE. Transactions On Image Processing, Vol. 13, No. 9, Sep (2004).

DOI: 10.1109/tip.2004.833105

[4] Yongsheng Xu, Shuwen Wang. Image Inpainting Based on Color Differences and Structure Differences. 3rd International Conference on Computer Science and Network Technology. 364-368.

DOI: 10.1109/iccsnt.2013.6967130

[5] Jian Sun, Jia J Y. Image completion with structure propagation. Proc Of the ACM Siggraph'05 , 2005, pp.861-868.

[6] Yongsheng Xu, Shuwen Wang. Vehicle Video Detection Based on Pulsed Coupled Neural Network. The 2014 7th International Congress on Image and Signal Processing. 832-836.

DOI: 10.1109/cisp.2014.7003874

[7] Yide Ma, Lian Li, Kun Zhan, Zhaobin Wang. Pulse coupled neural networks and image processing. Beijin: Science and Technology Press. 2008, 7.

[8] Changrong Zhao, Yide Ma, Kun Zhan. Three-state cascading pulse coupled neural network and the application in finding shortest paths. Systems Engineering and Electronics. 2008, 9, Vol, 30, No. 9.

[9] Zhiyong Yang, Qiyun Zhou, Dingkang Zhou. Gray Image Edge Detection Method Based on PCNN. Computer Engineering and Applications. 2004. 21, 92-94.

[10] Jiyang Dong. Grayscale Image Edge Detection Based on Pulse-Coupled Neural Network. Computer Applications. Vo1. 23, No. 9, 2003. 9, 50-52.