Home

About

Advanced Search

Browse by Discipline

Scientific Societies

E-print Alerts

Add E-prints

E-print Network
FAQHELPSITE MAPCONTACT US


  Advanced Search  

 
Learning Multiscale Image Models Of 2D Object Benoit Perrin, Narendra Ahuja and Narayan Srinivasa
 

Summary: Learning Multiscale Image Models Of 2D Object
Classes
Benoit Perrin, Narendra Ahuja and Narayan Srinivasa
The Beckman Institute for Advanced Science and Technology
University of Illinois at Urbana-Champaign
405 N. Mathews Avenue, Urbana, IL 61801
Abstract
This paper isconcerned with learning the canonical gray scalestructure of the images of
a classof objects. Structure is defined in terms of the geometry and layout of salientimage
regions that characterize the given views of the objects. The use of such structure based
learning of object appearence is motivated by the relativestabilityof image structureover
intensityvalues. A multiscale segmentation tree description isantomatically extracted for
all sample images which are then matched to construct a singlecanonical representative
which servesas the model 0fthe class. Differentimages are selectedas prototypes, and each
prototype tree is refined to best match the rest of the class. The model tree for the class
is that tree which is best supported over all the initializationswith differentprototypes.
Matching is formulated as a problem of finding the best mapping from regions of example
images to those of the model tree, and implemented as a problem in incremental refinement
of the model tree using a learning approach. Experiments are reported on a face image
database. The results demonstrate that a reasonable model offacial geometry and topology

  

Source: Ahuja, Narendra - Department of Electrical and Computer Engineering, University of Illinois at Urbana-Champaign

 

Collections: Computer Technologies and Information Sciences; Engineering