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

Show simple item record

dc.contributor.author Huang, Jinggang
dc.contributor.author Lee, Ann B.
dc.contributor.author Mumford, David Bryant
dc.date.accessioned 2010-03-18T15:19:50Z
dc.date.issued 2001
dc.identifier.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. en_US
dc.identifier.issn 0920-5691 en_US
dc.identifier.issn 1573-1405 en_US
dc.identifier.uri http://nrs.harvard.edu/urn-3:HUL.InstRepos:3720033
dc.description.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. en_US
dc.description.sponsorship Mathematics en_US
dc.language.iso en_US en_US
dc.publisher Springer Verlag en_US
dc.relation.isversionof doi:10.1023/A:1011109015675 en_US
dc.relation.hasversion http://www.stat.cmu.edu/~annlee/IJCV01_occlusions.pdf en_US
dash.license LAA
dc.subject natural images en_US
dc.subject stochastic image model en_US
dc.subject non-Gaussian statistics en_US
dc.subject scaling en_US
dc.subject dead leaves model en_US
dc.subject occlusions en_US
dc.subject clutter en_US
dc.title Occlusion Models for Natural Images: A Statistical Study of a Scale-Invariant Dead Leaves Model en_US
dc.type Journal Article en_US
dc.description.version Version of Record en_US
dc.relation.journal International Journal of Computer Vision en_US
dash.depositing.author Mumford, David Bryant
dc.date.available 2010-03-18T15:19:50Z

Files in this item

Files Size Format View
Mumford_OcclusionDeadLeaves.pdf 720.8Kb PDF View/Open

This item appears in the following Collection(s)

  • FAS Scholarly Articles [7588]
    Peer reviewed scholarly articles from the Faculty of Arts and Sciences of Harvard University

Show simple item record

 
 

Search DASH


Advanced Search
 
 

Submitters