Title: An Iterative $L_{1}$-Based Image Restoration Algorithm With an Adaptive Parameter Estimation
Abstract: Regularization methods for the solution of ill-posed inverse problems can be successfully applied if a right estimation of the regularization parameter is known. In this paper, we consider the <i xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">L</i> <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">1</sub> -regularized image deblurring problem and evaluate its solution using the iterative forward-backward splitting method. Based on this approach, we propose a new adaptive rule for the estimation of the regularization parameter that, at each iteration, dynamically updates the parameter value, following the evolution of the objective functional. The iterative algorithm automatically stops, without requiring any assumption about the perturbation process, when the parameter has reached a seemingly near optimal value. In spite of the fact that the optimality of this value has not yet been theoretically proved, a large number of numerical experiments confirm that the proposed rule yields restoration results competitive with those of the best state-of-the-art algorithms.
Publication Year: 2012
Publication Date: 2012-04-01
Language: en
Type: article
Indexed In: ['crossref', 'pubmed']
Access and Citation
Cited By Count: 23
AI Researcher Chatbot
Get quick answers to your questions about the article from our AI researcher chatbot