Design and implementation of optimized nearest neighbor classifiers for handwritten digit recognition

Author

Yan, Hong

Author_Institution

Dept. of Electr. Eng., Sydney Univ., NSW, Australia

fYear

1993

fDate

20-22 Oct 1993

Firstpage

10

Lastpage

13

Abstract

A method is described for handwritten digit recognition based on an optimized nearest-neighbor classification rule. In this method, a set of prototypes is obtained from training samples and is used to build a nearest-neighbor classifier. The classifier is then mapped to a multilayer perceptron. After training, the neural network is mapped back to a nearest-neighbor classifier with new and optimized prototypes. The classification procedure can be efficiently implemented without any multiplications

Keywords

character recognition; handwriting recognition; image classification; multilayer perceptrons; optimisation; handwritten digit recognition; multilayer perceptron; optimized nearest-neighbor classification rule; prototypes; training samples; Algorithm design and analysis; Design optimization; Handwriting recognition; Multi-layer neural network; Multilayer perceptrons; Nearest neighbor searches; Neural networks; Optimization methods; Prototypes; Testing;

fLanguage

English

Publisher

ieee

Conference_Titel

Document Analysis and Recognition, 1993., Proceedings of the Second International Conference on

Conference_Location

Tsukuba Science City

Print_ISBN

0-8186-4960-7

Type

conf

DOI

10.1109/ICDAR.1993.395793

Filename

395793