Non Negative K-SVD algorithm

Description

The NN-K-SVD algorithm finds a non-negative dictionary for linear representation of signals. Given a set of signals, it searches for the best dictionary that can sparsely represent each signal.

Detailed discussion on the algorithm and possible applications can be found in “K-SVD and its non-negative  variant for dictionary design”, written by M. Aharon, M. Elad, and A.M. Bruckstein  and appeared in the Proceedings of the SPIE conference wavelets, Vol. 5914, July 2005.

Implementation of the K-SVD and K-SVD denoise algorithms

K-SVD algorithm