Advanced search
1 file | 2.67 MB

Image denoising using mixtures of projected Gaussian scale mixtures

Bart Goossens (UGent) , Aleksandra Pizurica (UGent) and Wilfried Philips (UGent)
Author
Organization
Abstract
We propose a new statistical model for image restoration in which neighbourhoods of wavelet subbands are modeled by a discrete mixture of linear projected Gaussian Scale Mixtures (MPGSM). In each projection, a lower dimensional approximation of the local neighbourhood is obtained, thereby modeling the strongest correlations in that neighbourhood. The model is a generalization of the recently developed Mixture of GSM (MGSM) model, that offers a significant improvement both in PSNR and visually compared to the current state-of-the-art wavelet techniques. However the computation cost is very high which hampers its use for practical purposes. We present a fast EM algorithm that takes advantage of the projection bases to speed up the algorithm. The results show that, when projecting on a fixed data-independent basis, even computational advantages with a limited loss of PSNR can be obtained with respect to the BLS-GSM denoising method, while data-dependent bases of Principle Components offer a higher denoising performance, both visually and in PSNR compared to the current wavelet-based state-of-the-art denoising methods.
Keywords
MODELS, SIGNAL, NATURAL IMAGES, image denoising, Gaussian scale mixtures, SPARSE, STATISTICS, DOMAIN, Bayesian estimation

Downloads

  • (...).pdf
    • full text
    • |
    • UGent only
    • |
    • PDF
    • |
    • 2.67 MB

Citation

Please use this url to cite or link to this publication:

Chicago
Goossens, Bart, Aleksandra Pizurica, and Wilfried Philips. 2009. “Image Denoising Using Mixtures of Projected Gaussian Scale Mixtures.” Ieee Transactions on Image Processing 18 (8): 1689–1702.
APA
Goossens, B., Pizurica, A., & Philips, W. (2009). Image denoising using mixtures of projected Gaussian scale mixtures. IEEE TRANSACTIONS ON IMAGE PROCESSING, 18(8), 1689–1702.
Vancouver
1.
Goossens B, Pizurica A, Philips W. Image denoising using mixtures of projected Gaussian scale mixtures. IEEE TRANSACTIONS ON IMAGE PROCESSING. 2009;18(8):1689–702.
MLA
Goossens, Bart, Aleksandra Pizurica, and Wilfried Philips. “Image Denoising Using Mixtures of Projected Gaussian Scale Mixtures.” IEEE TRANSACTIONS ON IMAGE PROCESSING 18.8 (2009): 1689–1702. Print.
@article{1002612,
  abstract     = {We propose a new statistical model for image restoration in which neighbourhoods of wavelet subbands are modeled by a discrete mixture of linear projected Gaussian Scale Mixtures (MPGSM). In each projection, a lower dimensional approximation of the local neighbourhood is obtained, thereby modeling the strongest correlations in that neighbourhood. The model is a generalization of the recently developed Mixture of GSM (MGSM) model, that offers a significant improvement both in PSNR and visually compared to the current state-of-the-art wavelet techniques. However the computation cost is very high which hampers its use for practical purposes. We present a fast EM algorithm that takes advantage of the projection bases to speed up the algorithm. The results show that, when projecting on a fixed data-independent basis, even computational advantages with a limited loss of PSNR can be obtained with respect to the BLS-GSM denoising method, while data-dependent bases of Principle Components offer a higher denoising performance, both visually and in PSNR compared to the current wavelet-based state-of-the-art denoising methods.},
  author       = {Goossens, Bart and Pizurica, Aleksandra and Philips, Wilfried},
  issn         = {1057-7149},
  journal      = {IEEE TRANSACTIONS ON IMAGE PROCESSING},
  keyword      = {MODELS,SIGNAL,NATURAL IMAGES,image denoising,Gaussian scale mixtures,SPARSE,STATISTICS,DOMAIN,Bayesian estimation},
  language     = {eng},
  number       = {8},
  pages        = {1689--1702},
  title        = {Image denoising using mixtures of projected Gaussian scale mixtures},
  url          = {http://dx.doi.org/10.1109/TIP.2009.2022006},
  volume       = {18},
  year         = {2009},
}

Altmetric
View in Altmetric
Web of Science
Times cited: