1 October 2007 Estimating hyperparameters of mixture prior using hypothesis-testing problem and its applications to Bayesian image denoising
Author Affiliations +
J. of Electronic Imaging, 16(4), 043015 (2007). doi:10.1117/1.2804153
Abstract
We develop a spatially adaptive Bayesian image denoising method using a mixture of a Gaussian distribution and a point mass function at zero. In estimating hyperparameters, we present a simple and noniterative method. We use a hypothesis-testing technique in order to estimate the mixing parameter, the Bernoulli random variable. Based on the estimated mixing parameter, the variance for a clean signal is obtained by using the maximum generalized marginal likelihood (MGML) estimator. We simulate our denoising method using both orthogonal wavelet and dual-tree complex wavelet transforms and compare our algorithm to well-known denoising schemes. Experimental results show that the proposed method can generate good denoising results.
Il Kyu Eom, Yoo Shin Kim, Do Hoon Lee, "Estimating hyperparameters of mixture prior using hypothesis-testing problem and its applications to Bayesian image denoising," Journal of Electronic Imaging 16(4), 043015 (1 October 2007). http://dx.doi.org/10.1117/1.2804153
JOURNAL ARTICLE
8 PAGES


SHARE
KEYWORDS
Wavelets

Denoising

Wavelet transforms

Expectation maximization algorithms

Image denoising

Statistical analysis

Discrete wavelet transforms

RELATED CONTENT

Color transfer based on wavelet transform
Proceedings of SPIE (January 28 2008)
Texture discrimination using wavelets
Proceedings of SPIE (December 01 1991)
Tomographic imaging of time-varying distributions
Proceedings of SPIE (May 01 1990)

Back to Top