Industrial inspection using Gaussian functions in a colour space

被引：10

作者：

Bergasa, L ^{[1
]}

Duffy, N

Lacey, G

Mazo, M

机构：

[1] Univ Alcala de Henares, Escuela Politencn, Dept Elect, Madrid 28805, Spain

[2] Trinity Coll Dublin, Comp Vis & Robot Grp, Dublin, Ireland

来源：

IMAGE AND VISION COMPUTING | 2000年 / 18卷 / 12期

关键词：

colour object detection; Gaussian functions; colour clustering; competitive learning histogram; automated industrial inspection;

D O I：

10.1016/S0262-8856(00)00035-4

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

This paper presents an original method of modelling the colour distributions of images using 2D Gaussian functions and its application to flaw detection in industrial inspection. 2D Gaussian functions are used to model the colours that appear in the non-flawed images in an unsupervised manner. Pixels under test are compared to the colour distribution from training images. 140 images have been tested and the results are given. This method has a wide range of applications for detecting colour separable objects in images. It also has great potential in industrial inspection due to its speed, accuracy and unsupervised training. (C) 2000 Elsevier Science B.V. All rights reserved.

引用

页码：951 / 957

页数：7

共 11 条

[1] Automatic segmentation and classification of outdoor images using neural networks [J].

Campbell, NW ;

Thomas, BT ;

Troscianko, T .

INTERNATIONAL JOURNAL OF NEURAL SYSTEMS, 1997, 8 (01) :137-144

[2]

DUFFY N, 1997, IR MACH VIS IM PROC

[3]

DUFFY N, 1998, BRIT MACH VIS C P BM

[4]

GONG Y, 1995, COMPUTER VISION IMAG, V61, P260

[5] AN ANALYSIS OF THE GLVQ ALGORITHM [J].

GONZALEZ, AI ;

GRANA, M ;

DANJOU, A .

IEEE TRANSACTIONS ON NEURAL NETWORKS, 1995, 6 (04) :1012-1016

[6] Repairs to GLVQ: A new family of competitive learning schemes [J].

Karayiannis, NB ;

Bezdek, JC ;

Pal, NR ;

Hathaway, RJ ;

Pai, PI .

IEEE TRANSACTIONS ON NEURAL NETWORKS, 1996, 7 (05) :1062-1071

[7]

Kohonen T., 1995, Self-Organizing Maps

[8] Adaptive color segmentation - A comparison of neural and statistical methods [J].

Littmann, E ;

Ritter, H .

IEEE TRANSACTIONS ON NEURAL NETWORKS, 1997, 8 (01) :175-185

[9]

MOREIRA J, 1996, 9 SIBGRAPI U FED MIN

[10]

RODRIGEZ FJ, 1997, THESIS ALCALA

← 1 2 →