基于机器视觉的汽车安全带的表面缺陷检测系统
|
摘要
表面缺陷检测是汽车安全带质量检测中的关键环节之一,目前人工检测方法存在效率低、稳定性差的问题,无法满足实际检测需求。搭建一个汽车安全带表面缺陷检测平台,构建基于机器视觉的表面缺陷检测系统。针对汽车安全带的表面缺陷特征,提出一种基于频谱分析的特征提取方法,并讨论频域滤波器的选择和参数的计算。实验结果表明:频谱分析法同Bob特征分析法、直方图法等相比,能更好地满足汽车安全带表面缺陷检测的准确率和实时性要求。
Surface defect detection is one of the key links in the quality inspection of seat belt. At present,low efficiency and poor stability exist in artificial detection,so actual detection needs can not meet. The seat belt surface defect detection algorithm was explored based on image processing algorithms to meet the actual demand,and the seat belt surface defect detection system based on machine vision was constructed. Aiming at the characteristics of surface defect of seat belt,a method of feature extracting based on spectrum analysis was presented,and the selection of the filter and the calculation of the parameters were discussed. The experimental results show that the spectrum analysis method has better effect on the detection of surface defects than other detection methods,which can meet the requirements of real-time and accuracy.
Surface defect detection is one of the key links in the quality inspection of seat belt. At present,low efficiency and poor stability exist in artificial detection,so actual detection needs can not meet. The seat belt surface defect detection algorithm was explored based on image processing algorithms to meet the actual demand,and the seat belt surface defect detection system based on machine vision was constructed. Aiming at the characteristics of surface defect of seat belt,a method of feature extracting based on spectrum analysis was presented,and the selection of the filter and the calculation of the parameters were discussed. The experimental results show that the spectrum analysis method has better effect on the detection of surface defects than other detection methods,which can meet the requirements of real-time and accuracy.
引文
[1]槐向兵,厉征鑫,刘建立,等.基于轮廓波变换的织物疵点分割[J].计算机工程与设计,2014,35(6):2 153-2 158.HUAI X B,LI Z X,LIU J L,et al.Fabric Defect Segmentation Based on Contourlet Transform[J].Computer Engineering and Design,2014,35(6):2 153-2 158.
[2]王九各.基于图像分割的织物疵点检测与识别算法研究[D].郑州:中原工学院,2014.
[3]李冠志.基于机器视觉的织物瑕疵实时自动检测平台研究[D].上海:东华大学,2013.
[4]孙文立,刘金珠,金宏健.一种基于图像处理技术的坯布疵点检测及评估方法[J].纺织机械,2012(4):54-56.
[5]黄战华,刘正,李金晶,等.一种基于多通道Gabor滤波的纹理提取方法[J].仪器仪表学报,2009,30(4):694-698.HUANG Z H,LIU Z,LI J J,et al.Texture Extracting Approach Based on Multichannel Gabor Filters[J].Chinese Journal of Scientific Instrument,2009,30(4):694-698.
[6]徐增波,贡玉南,黄秀宝.基于二维连续小波变换的织物疵点检测[J].东华大学学报(自然科学版),2000,26(2):10-13.XU Z B,GONG Y N,HUANG X B.Fabric Defect Detection with Two Dimensional Continuous Wavelet Transform[J].Journal of Donghua University(Natural Science),2000,26(2):10-13.
[7]王丹.基于各向异性高斯滤波的图像边缘检测方法[D].西安:西安电子科技大学,2010.
[8]章为川.基于各向异性高斯核的图像边缘和角点检测[D].西安:西安电子科技大学,2013.
[2]王九各.基于图像分割的织物疵点检测与识别算法研究[D].郑州:中原工学院,2014.
[3]李冠志.基于机器视觉的织物瑕疵实时自动检测平台研究[D].上海:东华大学,2013.
[4]孙文立,刘金珠,金宏健.一种基于图像处理技术的坯布疵点检测及评估方法[J].纺织机械,2012(4):54-56.
[5]黄战华,刘正,李金晶,等.一种基于多通道Gabor滤波的纹理提取方法[J].仪器仪表学报,2009,30(4):694-698.HUANG Z H,LIU Z,LI J J,et al.Texture Extracting Approach Based on Multichannel Gabor Filters[J].Chinese Journal of Scientific Instrument,2009,30(4):694-698.
[6]徐增波,贡玉南,黄秀宝.基于二维连续小波变换的织物疵点检测[J].东华大学学报(自然科学版),2000,26(2):10-13.XU Z B,GONG Y N,HUANG X B.Fabric Defect Detection with Two Dimensional Continuous Wavelet Transform[J].Journal of Donghua University(Natural Science),2000,26(2):10-13.
[7]王丹.基于各向异性高斯滤波的图像边缘检测方法[D].西安:西安电子科技大学,2010.
[8]章为川.基于各向异性高斯核的图像边缘和角点检测[D].西安:西安电子科技大学,2013.