English

Sparse image representation by discrete cosine/spline based dictionaries

Numerical Analysis 2009-09-08 v1 Computer Vision and Pattern Recognition

Abstract

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.

Keywords

Cite

@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}
}
R2 v1 2026-06-21T13:43:34.919Z