These toolboxes combine Matlab M-code with optimized MEX functions written in C. The source code is freely available for academic and personal use. The toolboxes are designed to be easy to use, and are fully documented - see the readme.txt file in each toolbox to get started. Also see the faq.txt file in each toolbox for some frequently asked questions. If you have any additional questions or comments, don't hesitate to contact me. Enjoy!
Note: The packages will compile on Matlab v7.3 (R2006b) and up.
Implementation of the Batch-OMP and OMP-Cholesky algorithms for quick sparse-coding of large sets of signals [ref
Implementation of the Batch-OMP and OMP-Cholesky algorithms for sparse dictionaries [ref
Implementation of the K-SVD and Approximate K-SVD dictionary training algorithms, and the K-SVD Denoising algorithm [ref
]. Requires OMP-Box v10.
Implementation of the sparse K-SVD dictionary training algorithm and the sparse K-SVD Denoising algorithm [ref
]. Requires OMPS-Box v1. The package is also available without the demo volumes (less recommended) at KSVDS-Box v11-min
For an archive of previous versions, click here
Just For Fun:
A re-creation of Wendell Hicken's classic Scorched Earth
game in Matlab. The code experiments with some of Matlab's realtime user interface and animation abilities. Note that the code implements only the very basic functionality of the original game. Tested on Matlab R2010a.
The Matlab Scorch package is somewhat of a random outcome tracing back to the line ''I bet Scorched Earth can be coded in Matlab in just 3 days...'' :) The bet was in fact declared a success, though the current version is the result of several additional coding iterations.