Two-level adaptive denoising using Gaussian scale mixtures in overcomplete oriented pyramids
- 1 January 2005
- conference paper
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
Abstract
We describe an adaptive denoising method for images decomposed in overcomplete oriented pyramids. Our approach integrates two kinds of adaptation: 1) a 'coarse' adaptation, where a large window is used within each subband to estimate the local signal covariance; 2) a 'fine' adaptation, which uses small neighborhoods of coefficients modelled as the product of a Gaussian and a hidden multiplier, i.e., as Gaussian scale mixtures (GSM). The former provides adaptation to local spectral features, whereas the latter adapts to local energy fluctuations. We formulate our method as a Bayes least squares estimator using spatially variant GSMs. We also discuss the importance of image representation, compare the results using two different representations with complementary features, and study the effect of merging their results. We demonstrate through simulation that our method surpasses the state-of-the-art performance, in a L/sub 2/-norm sense.Keywords
This publication has 10 references indexed in Scilit:
- Full blind denoising through noise covariance estimation using gaussian scale mixtures in the wavelet domainPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2005
- Image denoising using scale mixtures of gaussians in the wavelet domainIEEE Transactions on Image Processing, 2003
- Bivariate shrinkage functions for wavelet-based denoising exploiting interscale dependencyIEEE Transactions on Signal Processing, 2002
- Spatially adaptive wavelet thresholding with context modeling for image denoisingPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Adaptive Wiener denoising using a Gaussian scale mixture model in the wavelet domainPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- A joint inter- and intrascale statistical model for Bayesian wavelet based image denoisingIEEE Transactions on Image Processing, 2002
- Low-complexity image denoising based on statistical modeling of wavelet coefficientsIEEE Signal Processing Letters, 1999
- Adaptive covariance estimation of locally stationary processesThe Annals of Statistics, 1998
- Wavelet-based image denoising using a Markov random field a priori modelIEEE Transactions on Image Processing, 1997
- Digital Image Enhancement and Noise Filtering by Use of Local StatisticsIeee Transactions On Pattern Analysis and Machine Intelligence, 1980