基于虚拟仪器的焊接缺陷自动检测系统  

Automatic Detection System for Welding Defect Based on LabVIEW

作　　者：王飞[1] 陈飞[1] 谢启[1] WANG Fei;CHEN Fei;XIE Qi(School of Electrical and Automatic Engineering,Changshu Institute of Technology,Changshu 215500,China)

机构地区：[1]常熟理工学院电气与自动化工程学院,江苏常熟215500

出　　处：《常熟理工学院学报》2021年第2期53-58,共6页Journal of Changshu Institute of Technology

摘　　要：针对复杂环境下焊接缺陷的自动检测需求,提出了一种逐层分割的自动检测方法.本方法利用形态学灰度重建对图像进行前景和背景的初次分割,然后利用轮廓的差分特性得到待检测对象的边缘以进行二次分割,进而对获取到的检测对象通过均值偏离法得到种子点,并在种子点上利用区域生长法最终得到弱小缺陷目标.最后通过实验验证了本文提出的检测系统对于焊接缺陷检测是有效的.Aiming at the problem of detecting welding defect under the complex environment,an automatic detection system based on the layer-by-layer segment is proposed.Firstly,the foreground and background of the image are segmented by morphological gray-scale reconstruction.Secondly,the edge of the object to be detected is obtained by using the difference characteristics of the contour,and then the seeds are obtained by means of mean deviation method for the acquired detection objects.Lastly,the dim targets are obtained by using the region growing method on the seeds.The experimental results show that the detection system proposed in this paper is effective for the detection of welding defect.

关 键 词：弱小目标 逐层分割 形态学重构 特征提取 LABVIEW 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]