Learning Appearance Based Models:
Mixtures of Second Moment Experts
Chris Bregler and Jitendra Malik
We devloped a new technique for object recognition based on learning
appearance models.
The image is decomposed into local regions which are described by a new
texture representation derived from the output of multiscale, multiorientation
filter banks. We call this representation
``Generalized Second Moments'' as it can be
viewed as a generalization of the windowed second moment matrix representation
used by Garding & Lindeberg.
Class-characteristic local texture features and their global composition is
learned by a hierarchical mixture of experts architecture (HME by Jordan
& Jacobs). The technique
is applied to a vehicle database consisting of 5 general car categories
(Sedan, Van with back-doors, Van without back-doors, old Sedan, and Volkswagen
Bug). This is a difficult problem with considerable in-class variation.
The new technique has a 6.5 %
misclassification rate, compared to eigen-images which give 17.4 %
misclassification rate, and nearest neighbors which give 15.7 %
misclassification rate.
- C. Bregler and J. Malik,
Learning Appearance Based Models: Hierarchical
Mixtures of Experts Approach based on Generalized Second Moments,
Technical Report UCB/CSD 96/897.
(ps.gz)
- C. Bregler, J. Malik, "Learning Appearance Based Models:
Mixtures of Second Moment Experts", to appear in
Advances in Neural Information Precessing Systems 9. (1996)
(ps.gz)
Chris Bregler (bregler@cs.berkeley.edu)