[1]赵凤霞,金少博,李纪峰,等.基于Blob分析的玻璃纤维织物缺陷检测方法研究[J].郑州大学学报(工学版),2015,36(06):90.[doi:10.3969/j.issn.1671-6833.2015.06.018]
　WANG Qinghai,ZHAO Fengxia,Ll Jifeng,et al.Research on Glass Fiber Fabric Defect Detection Method Based on Blob Analysis[J].Journal of Zhengzhou University (Engineering Science),2015,36(06):90.[doi:10.3969/j.issn.1671-6833.2015.06.018]
点击复制

基于Blob分析的玻璃纤维织物缺陷检测方法研究()
分享到：

《郑州大学学报(工学版)》[ISSN:1671-6833/CN:41-1339/T]

卷:
36
期数:
2015年06期
页码:
90
栏目:
出版日期:
2015-12-25

文章信息/Info

Title:
Research on Glass Fiber Fabric Defect Detection Method Based on Blob Analysis
作者:
赵凤霞2; 金少博2; 李纪峰2; 王庆海1
1.河南机电职业学院机械工程系，河南郑州451191; 2.郑州大学 机械工程学院，河南 郑州450001
Author(s):
WANG Qinghai1; ZHAO Fengxia2; Ll Jifeng2; JIN Shaobo2
1. Department of Mechanical Engineering，Henan Mechanical and Electrical Vocational College , Zhengzhou 451191， China; 2.School of Mechanical Engineering，Zhengzhou University，Zhengzhou 450001，China
关键词:
玻璃纤维织物; 在线检测; 缝隙缺陷; 机器视觉; Blob分析; Otsu算法
Keywords:
glass giber fabric;  on-line detection;  gap defect;  machine vision;  Blob analysis;  Otsu algorithm
DOI:
10.3969/j.issn.1671-6833.2015.06.018
文献标志码:
A
摘要:
为了解决玻璃纤维织物在线检测效率低、实时性差等问题，提出了一种基于Blob分析的织物缺陷检测方法．首先对织物图像采用均值滤波器进行平滑处理，以削弱噪声和织物纹理的干扰，然后采用Otsu 算法寻找最佳阈值将图像分割为Blob和背景的像素集合，采用形态学处理调整分割后的Blob形状，最后对图像进行连通性分析和特征提取，通过对Blob区域进行最小外接矩形拟合得到缺陷特征的个数和尺寸等信息．实验结果表明:该方法计算简单、检测结果稳健可靠、实时性好．
Abstract:
In order to solve the problems，such as low efficiency，poor real-time performance and so on，in on－line detection of glass fiber fabric，a new method of fabric defect detection based on Blob analysis is proposed． Firstly，the image is smoothed by using mean filter，and the noises and the fabric textures are weakened． Then，the Otsu algorithm is used to find the best threshold to segment the image into Blob and background pixels． The shape of the Blob region is adjusted by using morphological processing． Finally，the connectivity analysis and feature extraction of the image are carried out． The number and size of the defects are obtained by using the least square fitting of the Blob region． Experimental results show that the method is simple，reliable and robust．

参考文献/References:

［1］ AＲIVAZHAGAN S，GANESAN L，BAMA S． Fault segmentation in fabric images using Gabor wavelet transform［J］． Machine Vision and Applications，2006，16( 6) :356－363．

［2］ 朱俊岭，汪军，张孝南，等．基于AＲ 模型的机织物线状疵点研究［J］． 纺织学报，2012，33( 8) : 50－54．
［3］ 祝双武，郝重阳．基于纹理周期性分析的织物疵点检测方法［J］． 计算机工程与应用，2012，48(21) : 163－166

更新日期/Last Update: