Title :
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
fDate :
12/1/1996 12:00:00 AM
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;
Journal_Title :
Pattern Analysis and Machine Intelligence, IEEE Transactions on
