What is it

The iDUDE [1] is an information-theoretic image denoising algorithm. It is a specialization of the general DUDE (Discrete Universal DEnoiser) algorithm which formed the core of my Ms. Thesis [2], although it was started before by Giovanni Motta, and significantly improved, after my Ms. Thesis was over, by the other authors of the journal paper [2].

Note: the results shown on this site correspond to the version I developed during my Ms. Thesis [2], and are shown here as an example. If you want to compare your algorithm with the iDUDE, you should refer to the ones in the journal paper [1], which are better.


  1. Motta, G.; Ordentlich, E.; Ramirez, I.; Seroussi, G.; Weinberger, M.J.; , "The iDUDE Framework for Grayscale Image Denoising," Image Processing, IEEE Transactions on , vol.20, no.1, pp.1-21, Jan. 2011 doi: 10.1109/TIP.2010.2053939 [ieee]
  2. Ramirez, I., "The DUDE for continuous tone images", Ms. thesis, Facultad de Ingeniería, Universidad de la República - Dec. 2005 [pdf]

Last changed: September 27, 2012, 10:47 am

Constructive comments: nacho at fing dot edu dot uy

Valid HTML 4.01 Strict   ¡CSS Válido!