Mixed dictionaries generated by cosine and B-spline functions are considered. It is shown that, by highly nonlinear approaches such as Orthogonal Matching Pursuit, the discrete version of the proposed dictionaries yields a significant gain in the sparsity of an image representation.
@article{arxiv.0909.1310,
title = {Sparse image representation by discrete cosine/spline based dictionaries},
author = {James Bowley and Laura Rebollo-Neira},
journal= {arXiv preprint arXiv:0909.1310},
year = {2009}
}