A recursive soft-decision approach to blind image deconvolution

Abstract

Abstract-This paper presents a new approach to blind image deconvolution based on soft-decision blur identification and hierarchical neural networks. Traditional blind algorithms require a hard-decision on whether the blur satisfies a parametric form before their formulations. As the blurring function is usually unknown a priori, this precondition inhibits the incorporation of parametric blur knowledge domain into the restoration schemes. The new technique addresses this difficulty by providing a continual soft-decision blur adaptation with respect to the best-fit parametric structure throughout deconvolution. The approach integrates the knowledge of well-known blur models without compromising its flexibility in restoring images degraded by nonstandard blurs. An optimization scheme is developed where a new cost function is projected and minimized with respect to the image and blur domains. A nested neural network, called the hierarchical cluster model is employed to provide an adaptive, perception-based restoration. Its sparse synaptic connections are instrumental in reducing the computational cost of restoration. Conjugate gradient optimization is adopted to identify the blur due to its computational efficiency. The approach is shown experimentally to be effective in restoring images degraded by different blurs.

Restoration of Medical Images using Blind Image Deconvolution based on Ant Colony

“…ACO is used to detect the edges of the images, as the deblured images have ringing effect at its edges The ringing effect can be removed using edge taper function [13] which is used to preprocess our image before passing it to the debluring functions.…”

RBFN Based Motion Blur Parameter Estimation

“…In [8] bispectrum has been used to determine the blur parameters. In another approach, artificial neural networks such as Hopefield, multi layer feed-forward (MLF) and radial basis function (RBF) have been used for image restoration [11]. Many blind image restoration algorithms have been proposed [7].…”

Blind deblurring of natural images

“…A common approach is to restrict the problem to some blur model, such as motion blur or focus blur [8,9]. Among recent works on BID we emphasize [10,11,12,13]. Both [10] and [11] require extra data for a preliminary training.…”

“…Both [10] and [11] require extra data for a preliminary training. [12] attempts to encompass less restrictive blurs through a fuzzy technique, which is applied under the output of blur models known a priori. A non-iterative, fast method with proof of convergence is presented in [13].…”