Sciweavers

Share
ICIP
2008
IEEE

Localized and computationally efficient approach to shift-variant image deblurring

8 years 9 months ago
Localized and computationally efficient approach to shift-variant image deblurring
A new localized and computationally efficient approach is presented for shift/space-variant image restoration. Unlike conventional approaches, it models shift-variant blurring in a completely local form based on the recently proposed Rao Transform (RT). RT facilitates almost exact inversion of the blurring process locally and permits very fine-grain parallel implementation. The new approach naturally exploits the spatial locality of blurring kernels and smoothness of underlying focused images. It formulates the deblurring problem in terms of local parameters that are less correlated than raw image data. It is a fundamental advance that is general and not limited to any specific form of the blurring kernel such as a Gaussian. It has significant theoretical and computational advantages in comparison with conventional approaches such as those based on Singular Value Decomposition of blurring kernel matrices. Experimental results are presented for both synthetic and real image data. T...
Murali Subbarao, Youn-sik Kang, Satyaki Dutta, Xue
Added 30 May 2010
Updated 30 May 2010
Type Conference
Year 2008
Where ICIP
Authors Murali Subbarao, Youn-sik Kang, Satyaki Dutta, Xue Tu
Comments (0)
books