Current page: Information->Indexed and Annotated Bibliography
Enver Sanguineto
ABSTRACT
We propose a new approach to object classification based on the idea of geometric abstraction. A class of objects is described by means of a model which specifies the shape invariants common to all the members of the class. A model is a list of geometric constraints fixing the ranges in which local shape features can vary. We also propose an efficient algorithm for constraint satisfaction and we show the computational and descriptive advantages of our proposal with respect to other classification approaches based on average prototype models. 
ECVision indexed and annotated bibliography of cognitive computer vision publications
This bibliography was created by Hilary Buxton and Benoit Gaillard, University of Sussex, as part of ECVision Specific Action 8-1
The complete text version of this BibTeX file is available here: ECVision_bibliography.bib
An Abstract representation for Geometric knowledge for object classificationSite generated on Friday, 06 January 2006