Recognition of handwritten numerals by Quantum Neural Network with fuzzy features

被引：25

作者：

Zhou J. ^{[1
]}

Gan Q. ^{[2
]}

Krzyzak A. ^{[1
]}

Suen C.Y. ^{[1
]}

机构：

[1] Center for Pattern Recognition and Machine Intelligence, Concordia University, Montreal

[2] ISIS Research Group, University of Southampton

来源：

International Journal on Document Analysis and Recognition | 1999年 / 2卷 / 1期

关键词：

Decision-fusion system; Fuzzy classification; Handwritten numeral recognition; Morphing; Quantum Neural Network;

D O I：

10.1007/s100320050034

中图分类号：

学科分类号：

摘要：

This paper describes a new kind of neural network - Quantum Neural Network (QNN) - and its application to the recognition of handwritten numerals. QNN combines the advantages of neural modelling and fuzzy theoretic principles. Novel experiments have been designed for in-depth studies of applying the QNN to both real data and confusing images synthesized by morphing. Tests on synthesized data examine QNN's fuzzy decision boundary with the intention to illustrate its mechanism and characteristics, while studies on real data prove its great potential as a handwritten numeral classifier and the special role it plays in multi-expert systems. An effective decision-fusion system is proposed and a high reliability of 99.10% has been achieved. © 1999 Springer-Verlag Berlin Heidelberg.

引用

页码：30 / 36

页数：6

共 12 条

[1] Hull J.J., Commike A., Ho T.K., Multiple algorithms for handwritten character recognition, Proc. Int. Workshop on Frontiers in Handwriting Recognition, pp. 117-124, (1990)
[2] Suen C.Y., Nadal C., Mai T.A., Legault R., Lam L., Recognition of totally unconstrained handwritten numerals based on the concept of multiple experts, Proc. Int. Workshop on Frontiers in Handwriting Recognition, pp. 131-140, (1990)
[3] Suen C.Y., Nadal C., Legault R., Mai T.A., Lam L., Computer recognition of unconstrained handwritten numerals, Proc. of the IEEE, 80, pp. 1162-1180, (1992)
[4] Lam L., Suen C.Y., Optimal combinations of pattern recognition, Pattern Recognition Letters, 16, pp. 945-954, (1995)
[5] Zhou J., Gan Q., Suen C.Y., A high performance hand-printed numeral recognition system with verification module, Proc. ICDAR'97, 1, pp. 293-297, (1997)
[6] Gan Q., A neural network classifier with valid generalization performance, J. Southeast University, 24, pp. 67-72, (1994)
[7] Purushothaman G., Karayiannis N.B., Quantum Neural Networks (QNN's): Inherently fuzzy feedforward neural networks, IEEE Trans. on Neural Networks, 8, 3, pp. 679-693, (1997)
[8] Duda R.O., Hart P.E., Pattern Classification and Scene Analysis, (1973)
[9] Gomes J., Velho L., Image Processing For Computer Graphics, (1997)
[10] Suen C.Y., Shillman R.J., Low error rate optical character recognition of unconstrained handprinted letters based on a model of human perception, IEEE Trans. on Systems, Man and Cybernetics, pp. 491-495, (1977)

← 1 2 →