Blind deconvolution by a Newton method on the non‐unitary hypersphere
Author:
- 24 August 2012
- journal article
- research article
- Published by Wiley in International Journal of Adaptive Control and Signal Processing
- Vol. 27 (6) , 488-518
Abstract
SUMMARY: Blind deconvolution is an inverse filtering technique that has received increasing attention from academia as well as industry because of its theoretical implications and practical applications, such as in speech dereverberation, nondestructive testing and seismic exploration. An effective blind deconvolution technique is known as ‘Bussgang’, which relies on the iterative Bayesian estimation of the source sequence. Automatic gain control in blind deconvolution keeps constant the energy of the inverse filter impulse response and controls the magnitude of the estimated source sequence. The aim of the present paper is to introduce a class of Newton‐type algorithms to optimize the Bussgang cost function on the inverse‐filter parameter space whose geometrical structure is induced by the automatic‐gain‐control constraint. As the parameter space is a differentiable manifold, the Newton‐like optimization method is formulated in terms of differential geometrical concepts. The present paper also discusses convergence issues related to the introduced Newton‐type optimization algorithms and illustrates their performance on a comparative basis.Copyright © 2012 John Wiley & Sons, Ltd.Keywords
This publication has 26 references indexed in Scilit:
- Three-dimensional FLASH laser radar range estimation via blind deconvolutionJournal of Applied Remote Sensing, 2010
- A blind deconvolution approach to high-resolution mapping of transcription factor binding sites from ChIP-seq dataGenome Biology, 2009
- Neural learning by geometric integration of reduced ‘rigid-body’ equationsJournal of Computational and Applied Mathematics, 2004
- Analysis of Modified “Bussgang” Algorithms (MBAs) for Channel EqualizationIEEE Transactions on Circuits and Systems I: Regular Papers, 2004
- Fast Fixed-Point Neural Blind-Deconvolution AlgorithmIEEE Transactions on Neural Networks, 2004
- Blind deconvolution of ultrasonic signals in nondestructive testing applicationsIEEE Transactions on Signal Processing, 1997
- Performance of neural equalizers on partial erasure modelIEEE Transactions on Magnetics, 1997
- Super-exponential methods for blind deconvolutionIEEE Transactions on Information Theory, 1993
- Projected Newton methods and optimization of multicommodity flowsIEEE Transactions on Automatic Control, 1983
- Robust identification of a nonminimum phase system: Blind adjustment of a linear equalizer in data communicationsIEEE Transactions on Automatic Control, 1980