Improvements in Blind Image Restoration

Abstract

We present a revisal of blind image deconvolution technique for the restoration of linearly degraded images, without the explicit knowledge of either original image or the psf- the point spread function. Even the scenes which consist of finite support object over a uniformly black, white or grey background, this technique works fine. Occurrence includes certain types of medical imaging, astronomical imaging, and (1-D) gamma ray spectra processing. The only information that is required are the nonnegativity of the true image and the support size of the original object.
The restoration procedure involves recursive filtering of the blurred image to minimize a convex cost function. The new approach is experimentally shown to be more reliable and to have faster convergence than existing nonparametric ¯nite support blind deconvolution methods, for situations in which the exact object support is known.
This thesis covers the basic implementation of NAS-RIF method, using steepest descent, followed by implementation of swarm optimization technique- ACO, to optimize the results.