首页 | 本学科首页   官方微博 | 高级检索  
     

数字图像去模糊处理算法的对比研究
引用本文:刘扬阳,金伟其,苏秉华. 数字图像去模糊处理算法的对比研究[J]. 北京理工大学学报, 2004, 24(10): 905-909
作者姓名:刘扬阳  金伟其  苏秉华
作者单位:北京理工大学,信息科学技术学院光电工程系,北京,100081;北京理工大学,信息科学技术学院光电工程系,北京,100081;北京理工大学,信息科学技术学院光电工程系,北京,100081
基金项目:教育部跨世纪优秀人才培养计划 , 高等学校博士学科点专项科研项目
摘    要:为获得图像反卷积的真实解,考虑到噪声和模糊函数对复原图像的影响,研究分析了几种常用的数字图像去模糊处理技术,提出基于Markov约束的Poisson最大似然法(MPML)的超分辨力图像复原处理算法,并进行实际处理图像比较分析.实验表明:MPML算法具有其他几种算法的优势,同时减少了对原有信息的丢失.尤其是在噪声小的情况下,复原图像效果震荡条纹很小且具有较强的超分辨力复原能力.在数字图像去模糊处理技术研究方面具有一定意义.

关 键 词:去模糊  图像复原  MPML算法
文章编号:1001-0645(2004)10-0905-05
收稿时间:2003-11-04
修稿时间:2003-11-04

Comparison and Study of Image Deconvolution Algorithms
LIU Yang-yang,JIN Wei-qi and SU Bing-hua. Comparison and Study of Image Deconvolution Algorithms[J]. Journal of Beijing Institute of Technology(Natural Science Edition), 2004, 24(10): 905-909
Authors:LIU Yang-yang  JIN Wei-qi  SU Bing-hua
Affiliation:Department of Optical Engineering, School of Information Science and Technology, Beijing Institute of Technology, Beijing100081, China;Department of Optical Engineering, School of Information Science and Technology, Beijing Institute of Technology, Beijing100081, China;Department of Optical Engineering, School of Information Science and Technology, Beijing Institute of Technology, Beijing100081, China
Abstract:Deconvolution results may deviate true answers because of noise and low pass filtering. The effects of noise and blurred function to image data are compared and studied for several common deconvolution algorithms, and the maximum likelihood algorithm based on the Poisson-Markov model of super-resolution image restoration algorithms is proposed. Experiments showed that, based on the MPML algorithm proposed, it has the advantages of diminishing losses of original data in contrast to other algorithms, especially in cases involving lower noise. The recovery images display very small concussive lines and have better super-resolution recovery ability for deconvolution applications.
Keywords:deconvolution  image reconstruction  MPML algorithm
本文献已被 CNKI 万方数据 等数据库收录!
点击此处可从《北京理工大学学报》浏览原始摘要信息
点击此处可从《北京理工大学学报》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