Automatic feature generation for handwritten digit recognition

Author

Gader, Paul D. ; Khabou, Mohamed Ali

Author_Institution

Dept. of Electr. & Comput. Eng., Missouri Univ., Columbia, MO, USA

Volume

18

Issue

12

fYear

1996

fDate

12/1/1996 12:00:00 AM

Firstpage

1256

Lastpage

1261

Abstract

An automatic feature generation method for handwritten digit recognition is described. Two different evaluation measures, orthogonality and information, are used to guide the search for features. The features are used in a backpropagation trained neural network. Classification rates compare favorably with results published in a survey of high-performance handwritten digit recognition systems. This classifier is combined with several other high performance classifiers. Recognition rates of around 98% are obtained using two classifiers on a test set with 1000 digits per class

Keywords

backpropagation; feature extraction; image classification; neural nets; optical character recognition; search problems; automatic feature generation; backpropagation trained neural network; classification rates; evaluation measures; high-performance handwritten digit recognition systems; information measure; orthogonality; Backpropagation; Character generation; Character recognition; Entropy; Feature extraction; Handwriting recognition; Morphology; Multi-layer neural network; Neural networks; Testing;

fLanguage

English

Journal_Title

Pattern Analysis and Machine Intelligence, IEEE Transactions on

Publisher

ieee

ISSN

0162-8828

Type

jour

DOI

10.1109/34.546262

Filename

546262