Share Email Print

Proceedings Paper

Bilinear models of natural images
Author(s): Bruno A. Olshausen; Charles Cadieu; Jack Culpepper; David K Warland
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

Previous work on unsupervised learning has shown that it is possible to learn Gabor-like feature representations, similar to those employed in the primary visual cortex, from the statistics of natural images. However, such representations are still not readily suited for object recognition or other high-level visual tasks because they can change drastically as the image changes to due object motion, variations in viewpoint, lighting, and other factors. In this paper, we describe how bilinear image models can be used to learn independent representations of the invariances, and their transformations, in natural image sequences. These models provide the foundation for learning higher-order feature representations that could serve as models of higher stages of processing in the cortex, in addition to having practical merit for computer vision tasks.

Paper Details

Date Published: 7 February 2007
PDF: 10 pages
Proc. SPIE 6492, Human Vision and Electronic Imaging XII, 649206 (7 February 2007); doi: 10.1117/12.715515
Show Author Affiliations
Bruno A. Olshausen, Univ. of California/Berkeley (United States)
Charles Cadieu, Univ. of California/Berkeley (United States)
Jack Culpepper, Univ. of California/Berkeley (United States)
David K Warland, Univ. of California/Davis (United States)

Published in SPIE Proceedings Vol. 6492:
Human Vision and Electronic Imaging XII
Bernice E. Rogowitz; Thrasyvoulos N. Pappas; Scott J. Daly, 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?