四川大学学报（自然科学版）2011，Vol.48Issue(5)：1081-1086,6.DOI:10.3969/j.issn.0490-6756.2011.05.020
结合优化算法的神经网络图像复原算法
Image restoration method based on neural network combining with optimization algorithms
李伟 1王正勇 1余艳梅1
作者信息
- 1. 四川大学电子信息学院图象信息研究所,成都610064
- 折叠
摘要
Abstract
Image restoration method based on neural network combines with GA and image restoration method based on neural network combines with PSO are proposed, and t,heir effects of image restoration are compared too. First, the structure of the neural network are optimized by optimization algorithms. Second, nonlinear mapping relationships between the blurred image and clear image are established by training the optimized neural network which has the ability of learning and generalizing with a group of sample image. At Last, blurred image which needs restoring could be restored by the trained evolving neural network. The results of experiments demonstrate that this method has a satisfying restoration effect both in visual impression and quantitative analysis.关键词
图像复原/神经网络/遗传算法/PSO算法Key words
image restoration/neural network/genetic algorithm/PSO algorithm分类
信息技术与安全科学引用本文复制引用
李伟,王正勇,余艳梅..结合优化算法的神经网络图像复原算法[J].四川大学学报（自然科学版）,2011,48(5):1081-1086,6.
