首页 | 本学科首页   官方微博 | 高级检索  
     

基于Fourier神经网络的图像复原算法*
引用本文:田启川,田茂新.基于Fourier神经网络的图像复原算法*[J].计算机应用研究,2012,29(3):1143-1145.
作者姓名:田启川  田茂新
作者单位:太原科技大学电子信息工程学院,太原,030024
基金项目:山西省自然科学基金资助项目(2008011030);山西省回国留学人员科研资助项目(2011-075);太原市大学生创新创业专项项目(2010,2011);太原科技大学校UIT项目(XJ2010040)
摘    要:由于退化图像的点扩散函数难以准确确定,提出一种基于Fourier正交基函数的前向神经网络图像复原模型,该模型以一组Fourier正交基为隐层神经元的激励函数,根据误差传递算法进行权值修正,达到收敛目标。给出Fourier神经网络及其相应的衍生算法的图像恢复实现步骤。实验表明,该方法能较好地实现图像的复原。

关 键 词:图像复原  傅里叶正交基函数  傅里叶神经网络  衍生算法

Image restoration algorithm based on Fourier neural network
TIAN Qi-chuan,TIAN Mao-xin.Image restoration algorithm based on Fourier neural network[J].Application Research of Computers,2012,29(3):1143-1145.
Authors:TIAN Qi-chuan  TIAN Mao-xin
Affiliation:(College of Electronic & Information Engineering,Taiyuan University of Science & Technology,Taiyuan 030024,China)
Abstract:According to the fact that PSF(point spread function) of the degraded image can’t obtain accurately,this paper constructed a feed-forward neural network for image restoration based on the Fourier orthogonal function.The hidden-layer neurons were activated by a series of Fourier orthogonal functions,updated its weight by the error back-propagation training algorithm and finally reached convergence target.This paper applied the Fourier neural network and its hidden-neuron growing algorithm to recover the fuzzy image.Experiments show they have better performances on image restoration.
Keywords:image restoration  Fourier orthogonal function  Fourier neural network  hidden-neuron growing algorithm
本文献已被 CNKI 万方数据 等数据库收录!
点击此处可从《计算机应用研究》浏览原始摘要信息
点击此处可从《计算机应用研究》下载全文
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号