Sciweavers

Share
ICASSP
2008
IEEE

Robust image registration with illumination, blur and noise variations for super-resolution

12 years 4 months ago
Robust image registration with illumination, blur and noise variations for super-resolution
Super-resolution reconstruction algorithms assume the availability of exact registration and blur parameters. Inaccurate estimation of these parameters adversely affects the quality of the reconstructed image. However, traditional approaches for image registration are either sensitive to image degradations such as variations in blur, illumination and noise, or are limited in the class of image transformations that can be estimated. We propose an accurate registration algorithm that uses the local phase information, which is robust to the above degradations. We derive the theoretical error rate of the estimates in presence of non-ideal band-pass behavior of the filter and show that the error converges to zero over iterations. We also show the invariance of local phase to a class of blur kernels. Experimental results on images taken under varying conditions clearly demonstrates the robustness of our approach.
Himanshu Arora, Anoop M. Namboodiri, C. V. Jawahar
Added 30 May 2010
Updated 30 May 2010
Type Conference
Year 2008
Where ICASSP
Authors Himanshu Arora, Anoop M. Namboodiri, C. V. Jawahar
Comments (0)
books