Title: Restoration of motion blurred images

Authors: Pankaj Kumar Sa, Ratnakar Dash, Banshidhar Majhi

Addresses: Department of Computer Science and Engineering, National Institute of Technology Rourkela, Rourkela 769008, Orissa, India. ' Department of Computer Science and Engineering, National Institute of Technology Rourkela, Rourkela 769008, Orissa, India. ' Department of Computer Science and Engineering, National Institute of Technology Rourkela, Rourkela 769008, Orissa, India

Abstract: In most of the real life applications of imaging, the Point Spread Functions (PSFs) responsible for degrading the observed images are not known. Hence, PSF and image must be identified from the observed noisy blurred image. Here, we present a computationally simple iterative blind deconvolution algorithm that alternates between Fourier and spatial domain. During the iteration, the algorithm imposes some constraints making the results more accurate and visually more appealing than existing schemes. This method delivers good results for images having uniform as well as non-uniform background intensity. Experimental results are provided to validate the performance of the proposed scheme.

Keywords: image restoration; BID; blind image deconvolution; PSF; point spread function; motion blur; blurred images.

DOI: 10.1504/IJSISE.2009.029329

International Journal of Signal and Imaging Systems Engineering, 2009 Vol.2 No.1/2, pp.51 - 56

Received: 31 Jul 2008
Accepted: 24 Jan 2009
Published online: 19 Nov 2009 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article