1. Context adaptive image denoising through modeling of curvelet domain statistics
- Author
-
Wilfried Philips, Aleksandra Pizurica, Linda Tessens, Alin Alecu, Adrian Munteanu, Computational and Applied Mathematics Programme, and Electronics and Informatics
- Subjects
Transform theory ,image denoising ,business.industry ,Image quality ,curvelets ,Wavelet transform ,Pattern recognition ,Statistical model ,Context (language use) ,Atomic and Molecular Physics, and Optics ,Contourlet ,Computer Science Applications ,Wavelet ,Image statistics ,Computer Science::Computer Vision and Pattern Recognition ,Statistics ,Curvelet ,Artificial intelligence ,Electrical and Electronic Engineering ,business ,Mathematics - Abstract
In this paper, we perform a statistical analysis of curvelet coefficients, distinguishing between two classes of coefficients: those that contain a significant noise-free component, which we call "signal of interest", and those that do not. By investigating the marginal statistics, we develop a prior model for curvelet coefficients. The analysis of the joint intra- and inter-band statistics enables us to develop an appropriate local spatial activity indicator for curvelets. Finally, based on our findings, we present a novel denoising method, inspired by a recent wavelet domain method ProbShrink. The new method outperforms its wavelet-based counterpart and produces results that are close to those of state-of-the-art denoisers.
- Published
- 2008
- Full Text
- View/download PDF