Before using Python, I was using Matlab and I have developed some toolbox related to some papers ;) There were originally published on my previous website. I have decided to put them here, since I receive (few) emails from people asking for the code. I hope it can be useful. Please note I did not use them anymore, so don’t ask if it is not working on your Matlab version !
KMA package for Matlab
The package contains Matlab codes for learning the parameters of a Gaussian kernel function. The codes are based on the paper Approximation de matrices pour l’apprentissage des hyperparamètres des fonctions noyaux Gaussiennes: bz2.
Mahalanobis kernel package for Matlab
The package contains Matlab codes for learning the parsimonious Mahalanobis kernel. The codes eare based on the paper: Parsimonious Mahalanobis Kernel for the classification of high dimensional data: bz2.
Self complementary Area filter package for Matlab
The package contains Matlab codes to perform a self complementary area filtering. The codes are based on the paper Beyond self-duality in morphological image analysis of P. Soille and were used in A spatial-spectral kernel based approach for the classification of remote sensing images: bz2