基于图像处理技术的石油筛管割缝在线监测  

On-line detecting system of gaps in screen based on image progressing technology

作　　者：吴韡[1] 段发阶[1] 段晓杰[1] 徐赢[1] 

机构地区：[1]天津大学精密测试技术与仪器国家重点实验室,天津300072

出　　处：《电子技术应用》2014年第4期120-122,共3页Application of Electronic Technique

摘　　要：基于机器视觉技术,针对目前人工检测激光切割筛管的缝宽所存在的局限性和不确定性,设计了完整的实验测试设备。通过CCD相机对筛管割缝的图像进行采集,使用Sobel算法、Canny算法、高斯滤波等图像处理方法提取割缝宽度,实现了对割缝筛管的快速自动化高精度在线检测。试验结果表明,检测误差仅为17μm,为筛管的制造和使用行业提供了新的测量方法。According to the limitations and uncertainties of manunal vision inspection for gaps in laser-cut screen,a complete testing equipment was designed based on machine-vision. First of all, through CCD （charge-coupled device） camera, the images of gaps in screen were captured,then uhilizing the Sobel algorithm, Canny algorithm and Gaussian filter to extract width of the gaps. Finally,rapid automated on-line detecting system with high accuracy was actualized. The experimental results show that the error can be controlled within 17 μm. It provids a new method for the manufacture and application of screen.

关 键 词：石油筛管 割缝宽度 图像处理 高精度 在线检测 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]