Display options
Cite
Lyu S, Simoncelli EP. Modeling multiscale subbands of photographic images with fields of Gaussian scale mixtures. IEEE Trans Pattern Anal Mach Intell. 2009;31(4):693-706doi: 10.1109/TPAMI.2008.107.
Lyu, S., & Simoncelli, E. P. (2009). Modeling multiscale subbands of photographic images with fields of Gaussian scale mixtures. IEEE transactions on pattern analysis and machine intelligence, 31(4), 693-706. https://doi.org/10.1109/TPAMI.2008.107
Lyu, Siwei, and Simoncelli, Eero P. "Modeling multiscale subbands of photographic images with fields of Gaussian scale mixtures." IEEE transactions on pattern analysis and machine intelligence vol. 31,4 (2009): 693-706. doi: https://doi.org/10.1109/TPAMI.2008.107
Lyu S, Simoncelli EP. Modeling multiscale subbands of photographic images with fields of Gaussian scale mixtures. IEEE Trans Pattern Anal Mach Intell. 2009 Apr;31(4):693-706. doi: 10.1109/TPAMI.2008.107. PMID: 19229084; PMCID: PMC3718887.
Copy Download .nbib Format: NLM
Share it on

IEEE Trans Pattern Anal Mach Intell. 2009 Apr;31(4):693-706. doi: 10.1109/TPAMI.2008.107.

Modeling multiscale subbands of photographic images with fields of Gaussian scale mixtures.

IEEE transactions on pattern analysis and machine intelligence

Siwei Lyu, Eero P Simoncelli

Affiliations

  1. Computer Science Department, University at Albany, State University of New York, Albany, NY 12222, USA. [email protected]

PMID: 19229084 PMCID: PMC3718887 DOI: 10.1109/TPAMI.2008.107

Abstract

The local statistical properties of photographic images, when represented in a multi-scale basis, have been described using Gaussian scale mixtures. Here, we use this local description as a substrate for constructing a global field of Gaussian scale mixtures (FoGSMs). Specifically, we model multi-scale subbands as a product of an exponentiated homogeneous Gaussian Markov random field (hGMRF) and a second independent hGMRF. We show that parameter estimation for this model is feasible, and that samples drawn from a FoGSM model have marginal and joint statistics similar to subband coefficients of photographic images. We develop an algorithm for removing additive Gaussian white noise based on the FoGSM model, and demonstrate denoising performance comparable with state-of-the-art methods.

References

  1. IEEE Trans Image Process. 1995;4(7):932-46 - PubMed
  2. IEEE Trans Image Process. 1999;8(12):1688-701 - PubMed
  3. J Opt Soc Am A Opt Image Sci Vis. 2003 Jul;20(7):1237-52 - PubMed
  4. IEEE Trans Image Process. 2003;12(11):1338-51 - PubMed
  5. IEEE Trans Image Process. 2001;10(7):1056-68 - PubMed
  6. IEEE Trans Image Process. 2008 Jan;17(1):27-41 - PubMed
  7. Neural Comput. 2005 Feb;17(2):397-423 - PubMed
  8. J Opt Soc Am A. 1987 Dec;4(12):2379-94 - PubMed
  9. IEEE Trans Image Process. 2006 Dec;15(12):3736-45 - PubMed
  10. IEEE Trans Pattern Anal Mach Intell. 1984 Jun;6(6):721-41 - PubMed
  11. IEEE Trans Image Process. 1997;6(8):1089-102 - PubMed

Publication Types

Grant support