Using Mixtures of Factor Analyzers for
Segmentation and Pose Estimation
Geoffrey Hinton and Michael Revow
Department of Computer Science
University of Toronto
Abstract
To read a hand-written digit string, it is helpful to segment the
image into separate digits. Bottom-up segmentation heuristics often fail when neighboring
digits overlap substantially. We describe a system that has a stochastic generative model
of each digit class and we show that this is the only knowledge required for segmentation.
The system uses Gibbs sampling to construct a perceptual interpretation of a digit string
and segmentation arises naturally from the 'explaining away' effects that occur during
Bayesian inference. By using conditional mixtures of factor analyzers, it
is possible to extract an explicit, compact representation of the instantiation parameters
that describe the pose of each digit. These instantiation parameters can then be used as
the inputs to a higher level system that models the relationships between digits. The same
technique could be used to model individual digits as redundancies between the
instantiation parameters of their parts.
Download [ps.gz] [pdf]
Advances in Neural Information Processing Systems 9. MIT Press,
Cambridge MA.
[home page] [publications]