Note: Elias Pampalk is not working at OFAI anymore. These pages are no longer updated and kept for archiving purposes only. For any further information, please visit Elias Pampalk's current personal webpage.

 Last Updated: 04.07.2002


The SDH Toolbox contains several functions to calculate and visualize Smoothed Data Histograms. Some functions rely on functions of the SOM Toolbox. For details on each function try typing "help <function>" or for full details try "type <function>" after installing the toolbox, in the Matlab environment.

The main functions of the SDH Toolbox are:


The function to calculate SDHs is "sdh_calculate".
The main parameters are method and spread. The following methods are implemented k-Nearest Neighbor "knn" where the spread (=k) closest model vectors are voted for. Furthermore, two ranking methods are implemented, namely "1/n" and "ranking". With "1/n" the spread nearest model vectors are ranked and the votes are weighted as "1/n" where "n" is the rank. The "ranking" method directly uses the weighting "-n".
The function returns a data structure which includes the parameters used and the SDH matrix for visualization.


The function to visualize SDHs is "sdh_visualize".
The interpolation type can be set, a grid can be added, the SDH can be visualized using contours or, for example, the islands metaphor. Furthermore, it is possible to plot labels oo the map.


To demonstrate the usage and some of the possibilities a few demonstrations are supplied with the toolbox. The functions are "sdh_demo1", "sdh_demo2", and "sdh_demo3". For details on how the demonstrations call other functions use "type <function>". The documented demonstrations are available on this web page.


There are several functions which are used by other functions ("sdh_addframe", "sdh_colormap", "sdh_gmm_em", "sdh_gmm_em_mu", "sdh_gmm_init", "sdh_gmm_pdf", and "sdh_visualize_kmeans"). Furthermore a music dataset is supplied ("music.mat") see also