7 February 2007 Bilinear models of natural images
Author Affiliations +
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.
© (2007) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Bruno A. Olshausen, Charles Cadieu, Jack Culpepper, David K Warland, "Bilinear models of natural images", Proc. SPIE 6492, Human Vision and Electronic Imaging XII, 649206 (7 February 2007); doi: 10.1117/12.715515; https://doi.org/10.1117/12.715515
PROCEEDINGS
10 PAGES


SHARE
RELATED CONTENT


Back to Top