基于灰度共生矩阵和稳健马氏距离的织物横档类疵点检测

被引：8

作者：

张向东 ^{[1
,2
]}

黄秀宝 ^{[1
]}

机构：

[1] 东华大学纺织学院

[2] 大连工业大学纺织轻工学院

来源：

东华大学学报(自然科学版) | 2009年 / 35卷 / 06期

关键词：

横档类疵点; 灰度共生矩阵; 最小中值平方估计; 稳健马氏距离;

D O I：

暂无

中图分类号：

TP391.41 [];

学科分类号：

080203 ;

摘要：

在分析横档类疵点纹理特点的基础上,提取织物纹理图像的灰度共生矩阵单特征值——对比度.利用最小中值平方估计的快速算法,获得正常织物纹理训练样本的稳健马氏距离,并应用契比晓夫不等式确定在一定置信度条件下判断待检织物为疵点的马氏距离的阈值.对8种不同纹理结构、织物密度和纱线线密度的织物进行了横档类疵点的检测,在90%置信度下,可检出90%以上的横档类疵点,误检率为3.28%,检测效果较好.

引用

页码：691 / 698

页数：8

共 10 条

[1]

Applying a co-occurrence matrix to automatic inspection of weaving density for woven fabrics. Lin J J. Textile Research Journal . 2002

[2]

Textural features for image classification. Haralick RM,Shanmugam K,Dinstein I. IEEE Transactions on Systems Man and Cybernetics . 1973

[3]

Fast Algorithmfor the Minimum Covariance Determinant Estimator. ROUSSEEUWPJ,DRIESSENKV. Technimetrics . 1999

[4]

Least MedianofSquaresRegression. ROUSSEEUWPJ. Journal of the American Statistical Association . 1984

[5]

Expert system to inspect fabric defects by pattern recognition. Yoshio Shimizu. IEEE Transactions on Pattern Recognition . 1990

[6]

Applying an ArtificialNeural NetworktoPatternRecogitioninFabric Defects. TSAII S,LINC H,LINJ J. Textile ResearchJournal . 1995

[7]

Preserving boundaries for image texture segmentation using grey level co-occurring probabilities. Rishi Jobanputra and David A. Clausi. Pattern Recognition . 2006

[8]

The textural analysis of gravity data using co-occurrence matrices. Cooper,G.. R. J. Computers and Geosciences . 2004

[9]

A vision system for surface roughness characterization using the gray level co-occurrence matrix. E.S.Gadelmawla. NDT and E International . 2004

[10]

Image Texture Analysis:Methods and Comparisons. BHARATILHM,LIUJ J,MACGREGORFJ. ChemometricsandIntelligent LaboratorySystems . 2004

← 1 →