Occlusion Models for Natural Images: A Statistical Study of a Scale-Invariant Dead Leaves Model

DSpace/Manakin Repository

Occlusion Models for Natural Images: A Statistical Study of a Scale-Invariant Dead Leaves Model

Citable link to this page

. . . . . .

Title: Occlusion Models for Natural Images: A Statistical Study of a Scale-Invariant Dead Leaves Model
Author: Huang, Jinggang; Lee, Ann B.; Mumford, David Bryant

Note: Order does not necessarily reflect citation order of authors.

Citation: Lee, Ann B, David Bryant Mumford, and Jinggang Huang. 2001. Occlusion models for natural images: A statistical study of a scale-invariant dead leaves model. International Journal of Computer Vision 41(1-2): 35-59.
Full Text & Related Files:
Abstract: We develop a scale-invariant version of Matheron's “dead leaves model” for the statistics of natural images. The model takes occlusions into account and resembles the image formation process by randomly adding independent elementary shapes, such as disks, in layers. We compare the empirical statistics of two large databases of natural images with the statistics of the occlusion model, and find an excellent qualitative, and good quantitative agreement. At this point, this is the only image model which comes close to duplicating the simplest, elementary statistics of natural images—such as, the scale invariance property of marginal distributions of filter responses, the full co-occurrence statistics of two pixels, and the joint statistics of pairs of Haar wavelet responses.
Published Version: doi:10.1023/A:1011109015675
Other Sources: http://www.stat.cmu.edu/~annlee/IJCV01_occlusions.pdf
Terms of Use: This article is made available under the terms and conditions applicable to Other Posted Material, as set forth at http://nrs.harvard.edu/urn-3:HUL.InstRepos:dash.current.terms-of-use#LAA
Citable link to this page: http://nrs.harvard.edu/urn-3:HUL.InstRepos:3720033

Show full Dublin Core record

This item appears in the following Collection(s)

  • FAS Scholarly Articles [7262]
    Peer reviewed scholarly articles from the Faculty of Arts and Sciences of Harvard University
 
 

Search DASH


Advanced Search
 
 

Submitters