• Complex
  • Title
  • Keyword
  • Abstract
  • Scholars
  • Journal
  • ISSN
  • Conference
搜索

Author:

Xiong, Ruiqin (Xiong, Ruiqin.) | Ding, Wenpeng (Ding, Wenpeng.) | Ma, Siwei (Ma, Siwei.) | Gao, Wen (Gao, Wen.)

Indexed by:

EI Scopus

Abstract:

Image deblurring is an ill-posed linear inverse problem. Most traditional algorithms suffer from severe ringing artifacts. Recent approaches handle this issue by regularization techniques based on assumed image prior models. This paper presents a new method to reduce the ringing artifacts, without introducing any image prior models. For this purpose, we revisit the deblurring problem, using a probabilistic graph to model the image formation process. We establish the link between iterative back-projection and belief propagation and show that the ringing artifacts are caused by error propagation. Based on these analysis, we introduce a method to measure the variance of an estimation image and further propose an error-variance aware deblurring algorithm. Experimental results demonstrate that the proposed algorithm is very effective in suppressing the ringing artifacts. © 2011 IEEE.

Keyword:

Inverse problems Image enhancement Errors Iterative methods

Author Community:

  • [ 1 ] [Xiong, Ruiqin]School of Electronic Engineering and Computer Science, Peking University, Beijing 100871, China
  • [ 2 ] [Ding, Wenpeng]College of Computer Science and Technology, Beijing University of Technology, Beijing 100124, China
  • [ 3 ] [Ma, Siwei]School of Electronic Engineering and Computer Science, Peking University, Beijing 100871, China
  • [ 4 ] [Gao, Wen]School of Electronic Engineering and Computer Science, Peking University, Beijing 100871, China

Reprint Author's Address:

Email:

Show more details

Related Keywords:

Source :

ISSN: 1522-4880

Year: 2011

Page: 701-704

Language: English

Cited Count:

WoS CC Cited Count: 0

SCOPUS Cited Count: 6

ESI Highly Cited Papers on the List: 0 Unfold All

WanFang Cited Count:

Chinese Cited Count:

30 Days PV: 2

Online/Total:398/5275718
Address:BJUT Library(100 Pingleyuan,Chaoyang District,Beijing 100124, China Post Code:100124) Contact Us:010-67392185
Copyright:BJUT Library Technical Support:Beijing Aegean Software Co., Ltd.