About MixEst

MixEst is an open-source MATLAB toolbox for mixture model estimation with emphasis on scalability, flexibility and ease of use. Its aim is to provide a workbench for experiments on mixture distributions by means of a simple and coherent API, along with extensive options that allow for maximum flexibility for expert users.

MixEst is developed by Reshad Hosseini and Mohamadreza Mash'al at the University of Tehran vision laboratory. It is released free of charge, under the GNU General Public License, version 3 or any later version.

If you publish work using MixEst, please cite the MixEst paper (not published yet!):

author = {Reshad Hosseini and Mohamadreza Mash'al},
title = {MixEst: An Estimation Toolbox for Mixture Models},
year = {to appear},
url = {http://visionlab.ut.ac.ir/mixest}

How to contribute?

Visit our GitHub page at https://github.com/utvisionlab/mixest.


We would like to acknowledge support for this project from the school of electrical and computer engineering, at the college of engineering, University of Tehran.

The Manopt toolbox by Nicolas Boumal and Bamdev Mishra has inspired various design aspects of MixEst, in addition to being used in the gradient-based parameter estimation algorithms.

MixEst website and documentation theme are based on themes by Start Bootstrap.

We would also like to thank Kaelin Colclasure for sharing her Jekyll style-sheet for MATLAB publish command.

Third-party code included in MixEst: