FAST RELATIVE NEWTON ALGORITHM FOR BLIND DECONVOLUTION OF IMAGES (TA-L2)

Author(s) : Alexander Bronstein (Technion - Israel Institute of Technology, Israel) Michael Bronstein (Technion - Israel Institute of Technology, Israel) Michael Zibulevsky (Technion - Israel Institute of Technology, Israel) Yehoshua Zeevi (Technion - Israel Institute of Technology, Israel)

Abstract : We present an efficient Newton-like algorithm for quasimaximum likelihood (QML) blind deconvolution of images, which exploits the sparse Hessian structure. We also present an optimal distribution-shaping approach (sparsification), which allows to use simple and convenient sparsity prior for a wide class of images. Simulation results prove the efficiency of the proposed method.

Menu