ARTICLE
Fleuret_PRL_2008/IDIAP
Multi-layer Boosting for Pattern Recognition
Fleuret, Francois
https://publications.idiap.ch/index.php/publications/showcite/Fleuret_Idiap-RR-76-2008
Related documents
Pattern Recognition Letter
30
237-241
2009
We extend the standard boosting procedure to train a two-layer classifier dedicated to handwritten char-
acter recognition. The scheme we propose relies on a hidden layer which extracts feature vectors on a
fixed number of points of interest, and an output layer which combines those feature vectors and the
point of interest locations into a final classification decision.
Our main contribution is to show that the classical AdaBoost procedure can be extended to train such a
multi-layered structure by propagating the error through the output layer. Such an extension allows for
the selection of optimal weak learners by minimizing a weighted error, in both the output layer and the
hidden layer. We provide experimental results on the MNIST database and compare to a classical unsu-
pervised EM-based feature extraction.
REPORT
Fleuret_Idiap-RR-76-2008/IDIAP
Multi-layer Boosting for Pattern Recognition
Fleuret, Francois
EXTERNAL
https://publications.idiap.ch/attachments/reports/2008/Fleuret_Idiap-RR-76-2008.pdf
PUBLIC
Idiap-RR-76-2008
2008
Idiap
December 2008
We extend the standard boosting procedure to train
a two-layer classifier dedicated to handwritten
character recognition. The scheme we propose
relies on a hidden layer which extracts feature
vectors on a fixed number of points of interest,
and an output layer which combines those feature
vectors and the point of interest locations into a
final classification decision.
Our main contribution is to show that the
classical AdaBoost procedure can be extended to
train such a multi-layered structure by
propagating the error through the output
layer. Such an extension allows for the selection
of optimal weak learners by minimizing a weighted
error, in both the output layer and the hidden
layer. We provide experimental results on the
MNIST database and compare to a classical
unsupervised EM-based feature extraction.