Home

About

Advanced Search

Browse by Discipline

Scientific Societies

E-print Alerts

Add E-prints

E-print Network
FAQHELPSITE MAPCONTACT US


  Advanced Search  

 
http://www.psi.toronto.edu Bayesian Painting by Numbers: Flexible Priors
 

Summary: http://www.psi.toronto.edu
Bayesian Painting by Numbers: Flexible Priors
for Colour-Invariant Object Recognition
Jeroen C. Chua, Inmar E. Givoni, Ryan P. Adams, Brendan J. Frey
June 9, 2011 PSI TR 2011001
Abstract
Generative models of images should take into account transformations of ge-
ometry and reflectance. Then, they can provide explanations of images that
are factorized into intrinsic properties that are useful for subsequent tasks,
such as object classification. It was previously shown how images and objects
within images could be described as compositions of regions called structural
elements or `stels'. In this way, transformations of the reflectance and illumi-
nation of object parts could be accounted for using a hidden variable that is
used to `paint' the same stel differently in different images. For example, the
stel corresponding to the petals of a flower can be red in one image and yel-
low in another. Previous stel models have used a fixed number of stels per
image and per image class. Here, we introduce a Bayesian stel model, the
colour-invariant admixture (CIA) model, which can infer different numbers of
stels for different object types, as appropriate. Results on Caltech101 images
show that this method is capable of automatically selecting a number of stels

  

Source: Adams, Ryan Prescott - Department of Electrical and Computer Engineering, University of Toronto
Frey, Brendan J. - Department of Electrical and Computer Engineering, University of Toronto

 

Collections: Computer Technologies and Information Sciences