Please use this identifier to cite or link to this item: https://doi.org/10.1109/CVPR.2008.4587537
DC FieldValue
dc.titleMotion blur identification from image gradients
dc.contributor.authorJi, H.
dc.contributor.authorLiu, C.
dc.date.accessioned2014-11-28T01:54:08Z
dc.date.available2014-11-28T01:54:08Z
dc.date.issued2008
dc.identifier.citationJi, H.,Liu, C. (2008). Motion blur identification from image gradients. 26th IEEE Conference on Computer Vision and Pattern Recognition, CVPR : -. ScholarBank@NUS Repository. <a href="https://doi.org/10.1109/CVPR.2008.4587537" target="_blank">https://doi.org/10.1109/CVPR.2008.4587537</a>
dc.identifier.isbn9781424422432
dc.identifier.urihttp://scholarbank.nus.edu.sg/handle/10635/111608
dc.description.abstractRestoration 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.
dc.description.urihttp://libproxy1.nus.edu.sg/login?url=http://dx.doi.org/10.1109/CVPR.2008.4587537
dc.sourceScopus
dc.typeConference Paper
dc.contributor.departmentMATHEMATICS
dc.contributor.departmentTEMASEK LABORATORIES
dc.description.doi10.1109/CVPR.2008.4587537
dc.description.sourcetitle26th IEEE Conference on Computer Vision and Pattern Recognition, CVPR
dc.description.page-
dc.identifier.isiutNOT_IN_WOS
Appears in Collections:Staff Publications

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

SCOPUSTM   
Citations

78
checked on Feb 19, 2021

Page view(s)

93
checked on Feb 13, 2021

Google ScholarTM

Check

Altmetric


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