期刊
IEEE TRANSACTIONS ON IMAGE PROCESSING
卷 20, 期 3, 页码 696-708出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TIP.2010.2073477
关键词
Filterbank; Gaussian noise; image denoising; MSE estimation; Poisson noise; thresholding; unbiased risk estimate
资金
- Center for Biomedical Imaging (CIBM) of the Geneva-Lausanne Universities
- EPFL
- Leenaards and Louis-Jeantet Foundations
- Swiss National Science Foundation [200020-109415]
- Hong Kong Research Grant Council [CUHK410209]
We propose a general methodology (PURE-LET) to design and optimize a wide class of transform-domain thresholding algorithms for denoising images corrupted by mixed Poisson-Gaussian noise. We express the denoising process as a linear expansion of thresholds (LET) that we optimize by relying on a purely data-adaptive unbiased estimate of the mean-squared error (MSE), derived in a non-Bayesian framework (PURE: Poisson-Gaussian unbiased risk estimate). We provide a practical approximation of this theoretical MSE estimate for the tractable optimization of arbitrary transform-domain thresholding. We then propose a pointwise estimator for undecimated filterbank transforms, which consists of subband-adaptive thresholding functions with signal-dependent thresholds that are globally optimized in the image domain. We finally demonstrate the potential of the proposed approach through extensive comparisons with state-of-the-art techniques that are specifically tailored to the estimation of Poisson intensities. We also present denoising results obtained on real images of low-count fluorescence microscopy.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据