Acoustic-optical Image Denoising Using Alpha-Stable Multivariate Shrinkage Function in the Contourlet Domain
Huimin Lu, Seiichi Serikawa, Lifeng Zhang, Shota Nakashima · 2013
We describe a method for removing acoustic-optical image noise, based on a statistical model of the decomposed contourlet coefficients. This method proposes an alpha-stable multivariate shrinkage (MS) probability density function to model neighborhood contourlet coefficients. Then, according to the proposed PDF model, we design a maximum a posteriori (MAP) estimator, which relies on a Bayesian statistics representation for the contourlet coefficients of acoustic-optical images. There are two obvious virtues of this method. Firstly, contourlet transform decomposition is prior to curvelettransform by using ellipse sampling grid. Secondly, non-Gaussian multivariate shrinkage model is more effective in presentation of the acoustic-optical image contourlet coefficients. Some comparisons with the best available results will be presented in order to illustrate the effectiveness of the proposed method.