期刊
ELECTRONICS LETTERS
卷 41, 期 6, 页码 308-309出版社
INST ENGINEERING TECHNOLOGY-IET
DOI: 10.1049/el:20057273
关键词
-
A novel space-variant neural network based on an autoregressive moving average process is proposed for blind image deconvolution. An extended cost function motivated by human visual perception is developed to identify simultaneously the blur and restore the image degraded by space-variant non-causal blur and additive white Gaussian noise. Since the blur affects various regions of the image differently, the image has been divided into blocks according to an assigned level of activity. This is shown to result in more effective enhancement of the textured regions while suppressing the noise in smoother backgrounds.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据