Open AccessRegularized Deblurring using Directional Prior with Sparse Representation
Author(s) -
Sanjay Dhar,
Mayank Srivastava,
Vivek Maik
Publication year - 2019
Publication title -
international journal of engineering and advanced technology
Language(s) - English
Resource type - Journals
ISSN - 2249-8958
DOI - 10.35940/ijeat.a1040.1291s319
Subject(s) - deblurring , augmented lagrangian method , deconvolution , blind deconvolution , prior probability , mathematical optimization , optimization problem , computer science , constraint (computer aided design) , focus (optics) , sparse approximation , image restoration , algorithm , representation (politics) , bilevel optimization , orientation (vector space) , domain (mathematical analysis) , mathematics , artificial intelligence , image (mathematics) , image processing , bayesian probability , physics , geometry , politics , law , political science , optics , mathematical analysis
Blind deconvolution defined as simultaneous estimation and removal of blur is an ill-posed problem that can be solved with well-posed priors. In this paper we focus on directional edge prior based on orientation of gradients. Then the deconvolution problem is modeled as L2-regularized optimization problem which seeks a solution through constraint optimization. The constrained optimization problem is done in frequency domain with an Augmented Lagrangian Method (ALM). The proposed algorithm is tested on various synthetic as well as real data taken from various sources and the performance comparison is carried out with other state of the art existing methods.