Research on Image Restoration Algorithm Base on ACO-BP Neural Network

Abstract:

This paper studies the traits of Ant Colony Algorithm and BP neural network, at the same time it combines the ant colony optimization algorithm with BP neural network and applies them at the image restoration. This algorithm solves some problems of BP, such that the BP algorithm gets in local minimum easily, the speed of convergence is slowly and sometimes brings oscillation effect etc. that is reason the quality of restored image can be improved significantly. Besides, the article details ACO-BP algorithm’s theory and steps, and apply the improved algorithm in the image restoration. which reduces the MSE(Mean Square Error) of the optimization algorithm, and makes the speed of convergence of BP neural network faster. This algorithm is validated validly by the method of Simulation .

• Periodical: Key Engineering Materials (Volumes 460-461)
• Pages: 136-141
• DOI: https://doi.org/10.4028/www.scientific.net/KEM.460-461.136
• Online since: January 2011
• Authors: Hong Ye Xue, Wei Li Ma
• Keywords: ACO-BP Algorithm, Ant Colony Algorithm (ACA), BP Neural Network (BPNN), Image Restoration

References

[1] Zhang Hang, Luo Xiong Ant Colony Optimization Algorithm for Situation and Prospect of the study [J]. Information and Control . 2004, 33 (3) : 318-324.

[2] Zhong-Ke Shi. Neural network control theory [M]. Shanxi: Northwest Industry University Press, (2000).

[3] Jiao Licheng. Neural network system theory [M]. Xi'an: Xidian University Press, (1990).

[4] HU Shou-ren. Introduction to Neural Networks [M]. Changsha: National Defense University Press, (1993).

[5] HU Shou-ren. Neural Network Application Technology [M]. Changsha: National Defense University Press, (1993).

[6] Zhou Kai Li, Yao-Hong Kang. Matlab neural network model and its simulation program design [M]. Beijing: Tsinghua University Press, ( 2007).

[7] Zhang L., Zhang Y., Yang Y. -M., Color images restoration with multi-layer morphological(MLM) neural network, presented at 2003 International Conference on Machine Learning and Cybernetics, Xi'an, China, (2003).

DOI: 10.1109/icmlc.2003.1260037

[8] Shang G, Zhong L., Chen L., Discussion about BP Neural Network Structure and Choice of Samples Training Parameter[J]. Journal of Wuhan University of Technology, (1997).

[9] DongJun. Based on BP neural network image restoration algorithm [Shuo]. Xi'an University of Technology, 2009. 4. 20.

[10] Dorigo, M. and L. Gambardella, Ant Colony System: A Cooperative Learning Approach to the Traveling Salesman Problem, IEEE Transactions on Evolutionary Computation, 1(1)53–66. (1997).

DOI: 10.1109/4235.585892

[11] Zhou Liangwen. BP neural network designing based on immunity genetic algorithm[J ] . Journal of Anhui Uni2 versity , 1999 , 123(1).

[12] LIU Shuan1 , MENGQing chun Fast Image Matching of Licence Plate Based on Genetic Algorithm and BP Network[J]. Journal of chinese information processing, 119(14)72-77, (2006).

[13] Marco Dorigo Vittorio Maniezzo and Alberto Colorni, Ant System: Optimization by a Colony of Cooperating Agents[C]. IEEE Trans on SMC, 1996, 26(1): 28-41.

DOI: 10.1109/3477.484436