File Exchange

image thumbnail

PURE-LET for Poisson image denoising

version (165 KB) by SANDEEP PALAKKAL
This is an implementation of the PURE-LET, recently proposed for Poisson image denoising.


Updated 25 May 2011

View License

PURE-LET has been recently proposed [1] as noise removal strategy from Poisson-count images. Specifically, PURE (Poisson unbiased risk estimator) is an unbiased estimate, defined in the Haar wavelet domain, of the mean-squared error between the original image and the estimated image. PURE-LET attempts to estimate the true image from the noisy image by minimizing PURE. PURE-LET involves inversion of a small size matrix.

[1] F. Luisier, C. Vonesch, T. Blu, M. Unser, "Fast Interscale Wavelet Denoising of Poisson-corrupted Images", Signal Processing, vol. 90, no. 2, pp. 415-427, February 2010.

Cite As

SANDEEP PALAKKAL (2021). PURE-LET for Poisson image denoising (, MATLAB Central File Exchange. Retrieved .

Comments and Ratings (3)

Alexander Schmid

Very nice submission ;) I have one question: Where in the code is it possible to change the sigma, like in the custom mode of the ImageJ Plugin? Do I have to adjust the filter kernels LoD, HiD (h, d)?

Brett Gyarfas

@Nia Just changed the graymax variable in psnr folder to graymax = 2^16-1;


Thank you for this submission. While it is working very well for 8-bits image, it does not work for 16 bits. How can I change it top work for that class of image ?

MATLAB Release Compatibility
Created with R2008a
Compatible with any release
Platform Compatibility
Windows macOS Linux

Community Treasure Hunt

Find the treasures in MATLAB Central and discover how the community can help you!

Start Hunting!