Activity Number:
|
137
|
Type:
|
Topic Contributed
|
Date/Time:
|
Monday, August 12, 2002 : 2:00 PM to 3:50 PM
|
Sponsor:
|
Section on Statistical Computing*
|
Abstract - #300779 |
Title:
|
The Complex Statistics of Natural Images
|
Author(s):
|
Ann Lee*+
|
Affiliation(s):
|
Brown University
|
Address:
|
Box F, Brown University, Providence, Rhode Island, 02912, USA
|
Keywords:
|
natural image statistics ; non-linear sparse coding ; microimages ; image probability models
|
Abstract:
|
A crucial question in vision research is how to best model and code natural images. In this talk, we will explore the empirical statistics of large sets of patches from images in a normal visual environment and ask what are the intrinsic structures and dimension of natural image data. A new picture of natural image statistics seems to emerge, where geometric primitives (such as edges, blobs, and bars) generate a complex hierarchy of non-linear manifolds where the data is densely concentrated in state space.
|
- The address information is for the authors that have a + after their name.
- Authors who are presenting talks have a * after their name.
Back to the full JSM 2002 program |