Visualization and Intelligent Systems Laboratory
VISLab

 

 

Contact Information

VISLab
Winston Chung Hall Room 216
University of California, Riverside
900 University Avenue
Riverside, CA 92521-0425


Tel: (951)-827-3954

CRIS
Bourns College of Engineering
UCR
NSF IGERT on Video Bioinformatics

UCR Collaborators:
CSE
ECE
ME
STAT
PSYC
ENTM
BIOL
BPSC
ECON
MATH
BIOENG
MGNT

Other Collaborators:
Keio University

Other Activities:
IEEE Biometrics Workshop 2014
IEEE Biometrics Workshop 2013
Worshop on DVSN 2009
Multibiometrics Book

Webmaster Contact Information:
Alex Shin
wshin@ece.ucr.edu

Last updated: July 1, 2017

 

 

Learning Probabilistic Appearance Models for Object Recognition

Presented by: Stephanie Fonder



As an alternative to reconstructing the 3D information as a model for object recognition, it is possible to use a set of 2D views as a model. Here the model has two levels, one corresponding to clusters of images representing different views and a second representing smaller variations due to presence, position, and measurements of features of the objects appearance. This is accomplished using incremental conceptual clustering algorithm to form the clusters and a generalization algorinthem for making a single description from the cluster of images. Information from features and their relations are used to speed up the search for a match in the model.