基于灰度值的异形构件激光切割缺陷检测
Detection of defects in laser cutting of irregular components based on grayscale value
张天成 1张春艳2
作者信息
- 1. 安徽机电职业技术学院,安徽 芜湖 241000
- 2. 蚌埠学院,安徽 蚌埠 233030
- 折叠
摘要
基于机器视觉构建了异形构件成像系统,通过摄像机模型获取异形构件切割图像,采用小波变换增强采集的图像后,计算图像的灰度值,从而增强缺陷区域与周围背景的灰度差异,分割缺陷区域,提高缺陷检测的有效性.完成缺陷区域的分割后,提取图像的纹理特征并输入到支持向量机中,完成异形构件激光切割缺陷分类检测.测试结果显示:该方法图像增强效果较好,可恢复图像的整体清晰度;对比度、相关性均在0.924以上;能量结果均在0.12以下,能精准完成异形构件的表面缺陷的分类识别.
Abstract
An imaging system for irregular components based on machine vision is established.Cutting images of ir-regular components are obtained through the camera model of the system.After wavelet transform is used to enhance the collected images,the grayscale value of the images is calculated,thereby enhancing the grayscale difference be-tween the defect area and the surrounding background,segmenting the defect area and improving the effectiveness of defect detection.After the segmentation of the defect area is completed,the texture features of the image are extrac-ted and input into the support vector machine to complete the laser cutting defect classification detection of irregular components.The test results show that this method has a good image enhancement effect and can restore the overall clarity of the image;The contrast and correlation are both above 0.924;The energy results are all below 0.12,ac-curately classifying and identifying surface defects of irregular components.
关键词
灰度值/异形构件/激光切割/缺陷检测/成像系统Key words
grayscale value/irregular components/laser cutting/defect detection/imaging system引用本文复制引用
基金项目
安徽省2020年质量工程项目校企合作实践教育基地(2020sjjd030)
出版年
2024
NETL
NSTL
万方数据