An efficient three-stage classifier for handwritten digit recognition
Date Issued
2004-08-23
Author(s)
Gjorgjevikj, Dejan
Chakmakov, Dushan
Abstract
This paper proposes an efficient three-stage classifier
for handwritten digit recognition based on NN (Neural
Network) and SVM (Support Vector Machine) classifiers.
The classification is performed by 2 NNs and one SVM.
The first NN is designed to provide a low misclassification rate using a strong rejection criterion. It is applied
on a small set of easy to extract features. Rejected patterns are forwarded to the second NN that uses additional, more complex features, and utilizes a wellbalanced rejection criterion. Finally, rejected patterns
from the second NN are forwarded to an optimized SVM
that considers only the “top k” classes as ranked by the
NN. This way a very fast SVM classification is obtained
without sacrificing the classifier accuracy. The obtained
recognition rate is among the best on the MNIST database
and the classification time is much better compared to the
single SVM applied on the same feature set.
for handwritten digit recognition based on NN (Neural
Network) and SVM (Support Vector Machine) classifiers.
The classification is performed by 2 NNs and one SVM.
The first NN is designed to provide a low misclassification rate using a strong rejection criterion. It is applied
on a small set of easy to extract features. Rejected patterns are forwarded to the second NN that uses additional, more complex features, and utilizes a wellbalanced rejection criterion. Finally, rejected patterns
from the second NN are forwarded to an optimized SVM
that considers only the “top k” classes as ranked by the
NN. This way a very fast SVM classification is obtained
without sacrificing the classifier accuracy. The obtained
recognition rate is among the best on the MNIST database
and the classification time is much better compared to the
single SVM applied on the same feature set.
File(s)![Thumbnail Image]()
Loading...
Name
download.pdf
Size
325.53 KB
Format
Adobe PDF
Checksum
(MD5):b7a9558591df4ef45c95c37d941620d0