Please use this identifier to cite or link to this item: https://doi.org/10.1109/CVPR.2008.4587537
Title: Motion blur identification from image gradients
Authors: Ji, H. 
Liu, C. 
Issue Date: 2008
Source: Ji, H.,Liu, C. (2008). Motion blur identification from image gradients. 26th IEEE Conference on Computer Vision and Pattern Recognition, CVPR : -. ScholarBank@NUS Repository. https://doi.org/10.1109/CVPR.2008.4587537
Abstract: Restoration of a degraded image from motion blurring is highly dependent on the estimation of the blurring kernel. Most of the existing motion deblurring techniques model the blurring kernel with a shift-invariant box filter, which holds true only if the motion among images is of uniform velocity. In this paper, we present a spectral analysis of image gradients, which leads to a better configuration for identifying the blurring kernel of more general motion types (uniform velocity motion, accelerated motion and vibration). Furthermore, we introduce a hybrid Fourier-Radon transform to estimate the parameters of the blurring kernel with improved robustness to noise over available techniques. The experiments on both simulated images and real images show that our algorithm is capable of accurately identifying the blurring kernel for a wider range of motion types. ©2008 IEEE.
Source Title: 26th IEEE Conference on Computer Vision and Pattern Recognition, CVPR
URI: http://scholarbank.nus.edu.sg/handle/10635/111608
ISBN: 9781424422432
DOI: 10.1109/CVPR.2008.4587537
Appears in Collections:Staff Publications

Show full item record
Files in This Item:
There are no files associated with this item.

SCOPUSTM   
Citations

62
checked on Jan 17, 2018

Page view(s)

17
checked on Jan 14, 2018

Google ScholarTM

Check

Altmetric


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.