摘要
针对钢卷尺生产过程中表面缺陷检测效率低下的问题,构建一套应用于实际工业环境下的基于机器视觉的钢卷尺表面缺陷在线检测系统。首先,设计一种实验检测平台用于获取钢卷尺表面的图像;然后,通过图像分割的数字图像处理手段准确定位钢卷尺区域轮廓;最后,采用基于灰度值的模板匹配算法、边缘检测算法及颜色聚类方法对预处理后的图像进行匹配和特征计算,实现对目标物体和区域图像的快速定位和特征提取。结果表明:该检测系统的正确率达95.83%,平均检测速度达5.025秒/根,基本代替了人工检测,为钢卷尺表面检测提供了一种检查正确率和效率较高的新方法。
Aiming at the low efficiency of surface defect detection in the production process of steel tape,this paper proposes to design a set of online detection system for surface defect of steel tape based on machine vision,which can be applied in actual industrial environment.Firstly,an experimental detection platform is designed to obtain the surface image of the steel tape.Then,the contour of the steel tape area is accurately located by digital image processing method of image segmentation.Finally,the template matching algorithm based on gray value,edge detection algorithm and color clustering method are used to match and calculate the features of the preprocessed image,so as to realize the fast location and feature extraction of the target object and regional images.The results show that the accuracy rate of the proposed detection system is 95.83%,and the average detection speed is 5.025 seconds/root,which basically replaces manual detection and provides a new method with high accuracy and efficiency for surface detection of steel tape.
作者
陈佳星
沈毅
周浩
邓晓辰
CHEN Jiaxing;SHEN Yi;ZHOU Hao;DENG Xiaochen(School of Mechanical Engineering and Automation,Zhejiang Sci-Tech University,Hangzhou 310018,China)
出处
《软件工程》
2022年第12期21-25,共5页
Software Engineering
关键词
机器视觉
钢卷尺
缺陷检测
图像处理
machine vision
steel tape
defect detection
image processing
