bluelogo.gif (1643 bytes)

home page
people
research
publications
seminars
travel
search
UCL

Instantiating Deformable Models with a Neural Net

Christopher K. I. Williams,  Michael Revow 
and Geoffrey E. Hinton
Department of Computer Science
University of Toronto

Abstract

Deformable models are an attractive approach to recognizing objects which have considerable within-class variability such as handwritten characters. However, there are severe search problems associated with fitting the models to data which could be reduced if a better starting point for the search were available. We show that by training a neural network to predict how a deformable model should be instantiated from an input image, such improved staring points can be obtained. This method has been implemented for a system that recognizes handwritten digits using deformable models and the results show that the search time can be significantly reduced without compromising recognition performance.

Download  [ps] [pdf]

Computer Vision and Image Understanding, Vol. 68, No. 1, Oct 1997, pp. 120-126

[home page]  [publications]