%0 Journal Article
%T Fast Image Restoration Algorithm Using Neural Network Based on Harmonic Model<br>基于调和模型的快速神经网络图像复原算法
%A WU Ya-dong
%A SUN Shi-xin
%A <br>吴亚东
%A 孙世新
%J 计算机应用研究
%D 2007
%I 
%X Traditional image restoration algorithm using neural network has some shortcomings was fond in experiments,such as blurring edges,low speed of convergence.A fast image restoration algorithm using neural network based on harmonic model was given.In this algorithm,this paper used harmonic model as regular term in image restoration model,and introduced the steepest descent method in update rule to accelerate the convergence of network.Experiment results show that the proposed algorithm could restore the degraded image while preserving the edge in a fast speed.
%K image restoration
%K neural network
%K harmonic model
%K image deblurring<br>图像复原
%K 神经网络
%K 调和模型
%K 去模糊
%K 原模型
%K 快速收敛
%K 神经网络
%K 图像复原
%K 算法
%K Harmonic
%K Model
%K Based
%K Neural
%K Network
%K Algorithm
%K Image
%K Restoration
%K 边缘特征
%K 实验
%K 能量
%K 方法
%K 最陡下降
%K 状态更新
%K 正则化
%K 收敛速度
%K 图像边缘
%K 模糊
%U http://www.alljournals.cn/get_abstract_url.aspx?pcid=5B3AB970F71A803DEACDC0559115BFCF0A068CD97DD29835&cid=8240383F08CE46C8B05036380D75B607&jid=A9D9BE08CDC44144BE8B5685705D3AED&aid=EF4AD2E7BFCF0B30F4D233E96CD2928C&yid=A732AF04DDA03BB3&vid=B91E8C6D6FE990DB&iid=B31275AF3241DB2D&sid=4C100B7696CE9E24&eid=1B97AE5098AEB49C&journal_id=1001-3695&journal_name=计算机应用研究&referenced_num=0&reference_num=8