DocumentCode :
3470965
Title :
A parallel image restoration algorithm based on Harmonic model using neural networks
Author :
Yadong Wu ; Hongying Zhang ; Sun, Yu ; Ahmad, Ishfaq ; Yang, Fan
Author_Institution :
Sch. of Comput. Sci. & Technol., Southwest Univ. of Sci. & Technol., Mianyang, China
fYear :
2010
fDate :
5-6 July 2010
Firstpage :
30
Lastpage :
33
Abstract :
In our previous work, an image restoration algorithm based on modified Hopfield neural network and harmonic model was proposed. But the computational complexity of the algorithm is high. In this paper, a parallel image restoration algorithm based on the Harmonic model using modified Hopfield neural network (MHNN) is developed. The proposed algorithm makes full use of the parallel computation performance of neural network and effectively reduces the computational complexity from O(n×L) to O(n). Numerous experimental results demonstrate that the proposed restoration algorithm outperforms the traditional restoration algorithm in terms of computational complexity.
Keywords :
Hopfield neural nets; computational complexity; harmonic analysis; image restoration; computational complexity; harmonic model; modified Hopfield neural network; parallel computation; parallel image restoration algorithm; Atmospheric modeling; Computational complexity; Computer science; Degradation; Hopfield neural networks; Image restoration; Least squares approximation; Neural networks; Neurons; Parallel algorithms;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Ubi-media Computing (U-Media), 2010 3rd IEEE International Conference on
Conference_Location :
Jinhua
Print_ISBN :
978-1-4244-6708-2
Type :
conf
DOI :
10.1109/UMEDIA.2010.5543938
Filename :
5543938
Link To Document :
بازگشت