Share Email Print

Proceedings Paper

Application of non-linear transform coding to image processing
Author(s): Jens Hocke; Erhardt Barth; Thomas Martinetz
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

Sparse coding learns its basis non-linearly, but the basis elements are still linearly combined to form an image. Is this linear combination of basis elements a good model for natural images? We here use a non-linear synthesis rule, such that at each location in the image the point-wise maximum over all basis elements is used to synthesize the image. We present algorithms for image approximation and basis learning using this synthesis rule. With these algorithms we explore the the pixel-wise maximum over the basis elements as an alternative image model and thus contribute to the problem of finding a proper representation of natural images.

Paper Details

Date Published: 10 February 2012
PDF: 8 pages
Proc. SPIE 8291, Human Vision and Electronic Imaging XVII, 829105 (10 February 2012); doi: 10.1117/12.908732
Show Author Affiliations
Jens Hocke, Univ. zu Lübeck (Germany)
Erhardt Barth, Univ. zu Lübeck (Germany)
Thomas Martinetz, Univ. zu Lübeck (Germany)

Published in SPIE Proceedings Vol. 8291:
Human Vision and Electronic Imaging XVII
Bernice E. Rogowitz; Thrasyvoulos N. Pappas; Huib de Ridder, Editor(s)

© SPIE. Terms of Use
Back to Top
Sign in to read the full article
Create a free SPIE account to get access to
premium articles and original research
Forgot your username?