基于机器视觉检测钢板板形图像处理方法研究.PDF

第21卷第6期 Vol.21 No.6 2018年6月 软件工程 SOFTWARE ENGINEERING Jun. 2018 文章编号：2096-1472(2018)-06-01-03 DOI:10.19644/ki.issn2096-1472.2018.06.001 基于机器视觉检测钢板板形的图像处理方法研究 1 2 2 2 许博文 ，唐 朝 ，张 田 ，李家栋 (1.东北大学中荷生物医学与信息工程学院，辽宁 沈阳 110819； 2.东北大学材料科学与工程学院，辽宁 沈阳 110819) 摘 要： 目前钢板淬火生产线的板形只能依赖人力手工测量。为了提高效率和精度，为淬火板形智能控制提供基 础，本项目研究了基于视觉识别的淬火钢板板形检测系统，开发了相关的图像处理算法。基于钢板图像特征提出一种改 进了的Canny边缘检测算法。改进后的Canny算法通过局部自适应阀值，能够有效去除噪声影响，得到高质量的激光条 纹边缘。 关键词：淬火板形；图像处理；边缘检测 中图分类号：TP391 文献标识码：A An Image Processing Method for Steel Plate Shape Detection Based on Machine Vision 1 2 2 2 XU Bowen ,TANG Chao ,ZHANG Tian ,LI Jiadong ( 1.School of Sino-Dutch Biomedical and Information Engineering ,Northeastern University ,Shenyang 110819,China ; 2.Materials Institute ,Northeastern University ,Shenyang 110819,China) Abstract:At present,the shape of steel plate in quenching production line can only be manually measured.In order to improve the efficiency and precision and provide the basis for the intelligent control of plate shape,a plate shape detection system based on visual recognition is studied,and a related image processing algorithm is developed.Based on the image features of steel plate,an improved Canny edge detection algorithm is proposed.The algorithm can calculate the adaptive threshold,remove the noise influence effectively and get the high quality fringe of laser stripe. Keywords:steel plate shape;imag