Analysis and application of a self-organising image recognition neural network

被引：3

作者：

Banarse, DS ^{[1
]}

France, I ^{[1
]}

Duller, AWG ^{[1
]}

机构：

[1] Univ Wales, Sch Elect Engn & Comp Syst, Bangor LL57 1UT, Gwynedd, Wales

来源：

ADVANCES IN ENGINEERING SOFTWARE | 2000年 / 31卷 / 12期

关键词：

self-organisation; neural networks; object classification; computer vision; on-line training; pattern recognition; face recognition; hand written digit recognition;

D O I：

10.1016/S0965-9978(00)00066-1

中图分类号：

TP39 [计算机的应用];

学科分类号：

081203 ; 0835 ;

摘要：

This paper investigates the effect of various feature extraction methods on the recognition ability of a self-organising neural network called Paradise when applied to the problems of the classification of face images and hand written character recognition. The feature extraction methods investigated are, oriented Gaussian filters, Gabor filters and oriented Laplacian of Gaussian (LoG) filters. The recognition results for the two applications are Shown to compare favourably with other techniques designed specifically for the two tasks. (C) 2000 Civil-Comp Ltd. and Elsevier Science Ltd. All rights reserved.

引用

页码：937 / 944

页数：8

共 6 条

[1] Vision Experiments with Neural Deformable Template Matching [J].

D.S. Banarse ;

A.W.G. Duller .

Neural Processing Letters, 1997, 5 (2) :41-49

[2] Deformation invariant visual object recognition: Experiments with a self-organising neural architecture [J].

Banarse, DS ;

Duller, AWG .

NEURAL COMPUTING & APPLICATIONS, 1997, 6 (02) :79-90

[3] RECOGNITION AND SEGMENTATION OF CONNECTED CHARACTERS WITH SELECTIVE ATTENTION [J].

FUKUSHIMA, K ;

IMAGAWA, T .

NEURAL NETWORKS, 1993, 6 (01) :33-41

[4]

HUSSAIN R, 1994, J CHEM SOC PAKISTAN, V16, P1

[5] The black box of organizational demography [J].

Lawrence, BS .

ORGANIZATION SCIENCE, 1997, 8 (01) :1-22

[6] APPLICATION OF THE ANNA NEURAL NETWORK CHIP TO HIGH-SPEED CHARACTER-RECOGNITION [J].

SACKINGER, E ;

BOSER, BE ;

BROMLEY, J ;

LECUN, Y ;

JACKEL, LD .

IEEE TRANSACTIONS ON NEURAL NETWORKS, 1992, 3 (03) :498-505

← 1 →