bluelogo.gif (1643 bytes)

home page

Using mixtures of deformable models to capture variations in hand printed digits

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


Deformable models are an attractive way for characterizing handwritten digits since they have relatively few parameters, are able to capture many topological variations, and incorporate much prior knowledge. We have described a system that uses learned digit models consisting of splines whose shape is governed by a small number of control points. Images can be classified by separately fitting each digit model to the image, and using a simple neural network to decide which model fits best. We use an elastic matching algorithm to minimize an energy function that includes both the deformation energy of the digit model and the log probability that the model would generate the inked pixels in the image. The use of multiple models for each digit can characterize the population of handwritten digits better. We show how multiple models may be used without increasing the time required for elastic matching.

Download: [Postscript] [pdf]

[home page]  [publications]