期刊名称：Carptahian Journal of Electronic and Computer Engineering
印刷版ISSN：1844-9689
电子版ISSN：2343-8908
出版年度：2012
卷号：5
期号：1
页码：5
语种：English
出版社：UT Press Publishing House, Technical University of ClujNapoca, Romania
摘要：The resolution of ultrasound medical images is yet an important problem despite of the researchers efforts. In this paper we presents a nonlinear blind deconvolution to eliminate the blurring effect based on the measured radio-frequency signal envelope. This algorithm is executed in two steps. Firslty we make an estimation for Point Spread Function (PSF) and, secondly we use the estimated PSF to remove, iteratively their effect. The proposed algorithm is a greedy algorithm, called also matching pursuit or CLEAN. The use of this algorithm is motivated beacause theorically it avoid the so called inverse problem, which usually needs regularization to obtain an optimal solution. The results are presented using 1D simulated signals in term of visual evaluation and nMSE in comparison with the two most kwown regularisation solution methods for least square problem, Thikonov regularization or l2-norm and Total Variation or l1 norm.
