ROTATION-INVARIANT NEURAL PATTERN-RECOGNITION SYSTEM WITH APPLICATION TO COIN RECOGNITION

被引：92

作者：

FUKUMI, M ^{[1
]}

OMATU, S ^{[1
]}

TAKEDA, F ^{[1
]}

KOSAKA, T ^{[1
]}

机构：

[1] GLORY LTD,HIMEJI 670,JAPAN

来源：

IEEE TRANSACTIONS ON NEURAL NETWORKS | 1992年 / 3卷 / 02期

关键词：

D O I：

10.1109/72.125868

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

In pattern recognition, we must often deal with problems to classify a transformed pattern. In this paper, we propose a neural pattern recognition system which is insensitive to rotation of input pattern by various degrees. The system consists of a fixed invariance network with many slabs and a trainable multilayered network. To illustrate the effectiveness of the system, we apply it to a rotation-invariant coin recognition problem to distinguish between a 500 yen coin and a 500 won coin. The results show that our neural network approach works well for variable rotation pattern recognition problem.

引用

页码：272 / 279

页数：8

共 24 条

[1]

[Anonymous], 1987, LEARNING INTERNAL RE

[2]

CARPENTER GA, 1988, IEEE COMPUT, V21, P77, DOI DOI 10.1109/2.33

[3]

COTTRELL GW, 1987, 8702 U CAL I COGN SC

[4]

CRUZ V, 1989, P INT JOINT C NEUR N, V2, P17

[5]

ELLIMAN G, 1990, P I ELECTR ENG, V137, P183

[6]

FUKUMI M, 1990, T IEICE JAPAN, P648

[7]

FUKUMI M, 1991, 13TH P INT SYST S TO, P53

[8]

FUKUMI M, 1989, P INT JOINT C NEURAL, V2, P611

[9] NEOCOGNITRON - A NEURAL NETWORK MODEL FOR A MECHANISM OF VISUAL-PATTERN RECOGNITION [J].

FUKUSHIMA, K ;

MIYAKE, S ;

ITO, T .

IEEE TRANSACTIONS ON SYSTEMS MAN AND CYBERNETICS, 1983, 13 (05) :826-834

[10]

HAYASHI Y, 1990, P INT NEURAL NETWORK, V2, P781

← 1 2 3 →