• 首页
  • 期刊简介
  • 编委会
  • 投稿指南
  • 收录情况
  • 杂志订阅
  • 联系我们
引用本文:吴 闯,于大泳.基于轮廓修补和图像差分的手机玻璃盖板表面缺陷检测[J].软件工程,2020,23(7):41-45.【点击复制】
【打印本页】   【下载PDF全文】   【查看/发表评论】  【下载PDF阅读器】  
←前一篇|后一篇→ 过刊浏览
分享到: 微信 更多
基于轮廓修补和图像差分的手机玻璃盖板表面缺陷检测
吴 闯,于大泳
(上海理工大学机械工程学院,上海 200093)
wuch19940805@163.com; wy_ydy@163.com
摘 要: 由于手机玻璃盖板每年出货量大,易产生表面缺陷,采用人工检测,效率低,同时传统表面缺陷检测算 法精度不高。为此,本文在研究了其他表面缺陷检测领域的图像处理算法后,提出一种基于轮廓修补和图像差分的手机 玻璃盖板表面缺陷检测算法,相较于传统的图像差分法,无须做图像配准处理,大大提高了算法的稳定性。在对原图像 进行自适应中值滤波和ROI区域提取后,应用本文提出的算法进行检测,结果表明,手机玻璃盖板表面常见的点、线类 缺陷都能被快速正确地检出。
关键词: 玻璃盖板;自适应中值滤波;轮廓修补;图像差分;缺陷检测
中图分类号: TP391    文献标识码: A
Surface Defect Detection of Mobile Phone Glass Cover based on Contour Repair and Image Difference
WU Chuang, YU Dayong
( School of Mechanical Engineering, University of Shanghai for Science and Technology, Shanghai 200093, China)
wuch19940805@163.com; wy_ydy@163.com
Abstract: Due to the large sales volume of mobile phone glass covers, which are prone to surface defects, the using of low-ef cient manual detection leads to the fact that the accuracy of traditional visual surface defect detection algorithm is not high. To solve the problem, this paper proposes a surface defect detection algorithm for mobile phone glass covers based on contour repair and image difference after studying image processing algorithms in other areas of surface defect detection. Compared with the traditional image difference method, no image matching Quasi-processing greatly improves the stability of the algorithm. After adaptive median ltering and ROI region extraction of the original image, the algorithm proposed in this paper is used for detection. The results show that the common points and line defects on the surface of the mobile phone glass cover can be quickly and correctly detected.
Keywords: glass cover; adaptive median filtering; contour repair; image difference; defects detection


版权所有:软件工程杂志社
地址:辽宁省沈阳市浑南区新秀街2号 邮政编码:110179
电话:0411-84767887 传真:0411-84835089 Email:semagazine@neusoft.edu.cn
备案号:辽ICP备17007376号-1
技术支持:北京勤云科技发展有限公司

用微信扫一扫

用微信扫一扫