Learning Sparse Multiscale Image Representations

  title={Learning Sparse Multiscale Image Representations},
  author={Phil Sallee and Bruno A. Olshausen},
We describe a method for learning sparse multiscale image representations using a sparse prior distribution over the basis function coefficients. The prior consists of a mixture of a Gaussian and a Dirac delta function, and thus encourages coefficients to have exact zero values. Coefficients for an image are computed by sampling from the resulting posterior distribution with a Gibbs sampler. The learned basis is similar to the Steerable Pyramid basis, and yields slightly higher SNR for the same… CONTINUE READING
Highly Cited
This paper has 107 citations. REVIEW CITATIONS


Publications citing this paper.
Showing 1-10 of 61 extracted citations

Monte Carlo Methods for Adaptive Sparse Approximations of Time-Series

IEEE Transactions on Signal Processing • 2007
View 9 Excerpts
Highly Influenced

Biologically-inspired characterization of sparseness in natural images

2016 6th European Workshop on Visual Information Processing (EUVIP) • 2016

Efficient Algorithms for Convolutional Sparse Representations

IEEE Transactions on Image Processing • 2016
View 1 Excerpt

Learning a multiscale patch-based representation for image denoising in X-RAY fluoroscopy

2016 IEEE International Conference on Image Processing (ICIP) • 2016
View 1 Excerpt

107 Citations

Citations per Year
Semantic Scholar estimates that this publication has 107 citations based on the available data.

See our FAQ for additional information.

Similar Papers

Loading similar papers…