一种陶瓷方形扁平封装外观缺陷检测方法
|
摘要
提出一种基于机器视觉的陶瓷方形扁平封装外观缺陷检测方法。对于封装外形尺寸较大而缺陷较细微的情形,将待检片分为多个区域与标准样片进行比对检测。首先通过Foerstner特征点检测法提取标准片图像的特征点,然后使用随机抽样一致性(RANSAC)图像匹配算法,将所有标准片图像拼接并融合生成一张标准片全幅面模板,再将待检片分区与标准片模板进行序贯比对,以提取可疑区域,最后利用支持向量机(SVM)分类器对可疑区域进行筛选分类。实验结果表明,这种方法不仅克服了传统视觉检测过程中视野范围与图像分辨率相互制约的矛盾,且对陶瓷方形扁平封装表面缺陷具有较高的检出率。
A machine-vision-based defect detection method for ceramic quad flat package appearance was proposed. For case of larger package size and smaller defects, the sample to be inspected was divided into several regions and compared with the standard sample. Firstly, the feature points of the standard image were extracted by Foerstner feature point detection method. Then all the standard images were stitched and merged by random sample consensus(RANSAC) image matching algorithm to generate a standard full-frame template. And then the sample to be inspected was compared with the standard template sequentially to extract the suspicious area. Finally the suspicious region was filtered and classified by using the support vector machine(SVM) classifier. The test results show that the proposed method can overcome the contradiction between the visual field range and the image resolution in the traditional visual inspection process, and has a high detection rate for the ceramic quad flat package surface defects.
A machine-vision-based defect detection method for ceramic quad flat package appearance was proposed. For case of larger package size and smaller defects, the sample to be inspected was divided into several regions and compared with the standard sample. Firstly, the feature points of the standard image were extracted by Foerstner feature point detection method. Then all the standard images were stitched and merged by random sample consensus(RANSAC) image matching algorithm to generate a standard full-frame template. And then the sample to be inspected was compared with the standard template sequentially to extract the suspicious area. Finally the suspicious region was filtered and classified by using the support vector machine(SVM) classifier. The test results show that the proposed method can overcome the contradiction between the visual field range and the image resolution in the traditional visual inspection process, and has a high detection rate for the ceramic quad flat package surface defects.
引文
[1] 徐奕,刘玉岭,王辰伟,等.阻挡层CMP过程中划伤缺陷的控制[J].半导体技术,2018,43(11):841-846.XU Y,LIU Y L,WANG C W,et al.Control of scratch defects during the barrier CMP [J].Semiconductor Technology,2018,43(11):841-846 (in Chinese).
[2] 徐健,孙悦,孙鹏,等.扇出型封装结构可靠性试验方法及验证[J].半导体技术,2018,43(10):787-794.XU J,SUN Y,SUN P,et al.Reliability test methods and verification of the fan-out package [J].Semiconductor Technology,2018,43(10):787-794(in Chinese).
[3] 夏链,贾伟妙,崔鹏,等.基于机器视觉的BGA芯片缺陷检测及其MATLAB实现[J].合肥工业大学学报(自然科学版),2009,32(11):1652-1655.XIA L,JIA W M,CUI P,et al. Defectsinspection and MATLAB realization of BGA chips based on machine vision [J].Journal of Hefei University of Technology,2009,32(11):1652-1655(in Chinese).
[4] 马旭,刘应安,业宁,等.基于核PCA与SVM算法的木材缺陷识别[J].常州大学学报(自然科学版),2017,29(03)::60-68.MA X,LIU Y A,YE N,et al. Application of KPCA and SVM to wood defect recognition[J].Journal of Changzhou University(Natural Science Edition),2017,29(03):60-68 (in Chinese).
[5] 刘晓昱,陈燕宁,李建强,等.适用于高密度封装的失效分析技术及其应用[J].半导体技术,2018,43(4):310-315.LIU X Y,CHEN Y N,LI J Q,et al.Failure analysis technology for high density packaging and its application [J].Semiconductor Technology,2018,43(4):310-315 (in Chinese).
[6] LIU C,QIAO F,YANG X H,et al.Hardware acceleration with pipelined adder for support vector machine classifier [C]// Proceedings of International Conference on Digital Information and Communication Technology and its Applications.Bangkok, Thailand,2014: 13-16.
[7] MANDAL B,SARMA M P,SARMA K K. Design of a systolic array based multiplierless support vector machine classifier[C]// Proceedings of International Conference on Signal Processing and Integrated Networks. Noida, India,2014:35-39.
[8] 王卫兵,白小玲,徐倩.SURF和RANSAC的特征图像匹配[J].哈尔滨理工大学学报,2018,23(1):117-121.WANG W B,BAI X L,XU Q. Features image matching of SURF and RANSAC [J]. Journal of Harbin University of Scienceand Technology,2018,23(1):117-121(in Chinese).
[9] SCHWEITZER H,RUI D,ANDERSON R F.A Dual-bound algorithm for very fast and exact template matching [J]. IEEE Transactions on Pattern Analysis & Machine Intelligence,2011,33(3):459-470.
[10] 吴鹏,徐洪玲,宋文龙.结合小波金字塔的快速NCC图像匹配算法[J].哈尔滨工程大学学报,2017,38(5):791-796.WU P,XU H L,SHONG W L. A fast NCC image matching algorithm based on wavelet pyramid search strategy [J]. Journal of Harbin Engineering University,2017,38(5):791-796(in Chinese).
[11] 汪威,何小凡,李浩然,等.一种包装卷材快速在线检测算法[J].包装工程,2018,39(5):146-152.WANG W,HE X F,LI H R,et al. A fast online detection algorithm for packaging coils [J]. Packaging Engineering,2018,39(5):146-152(in Chinese).
[12] 高向东,蓝重洲,陈子琴,等.焊接缺陷磁光成像动态检测与识别[J].光学精密工程,2017,25(5):1135-1141.GAO X D,LAN C Z,CHEN Z Q,et al.Dynamic detection and recognition of welded defects based on magneto-optical imaging [J]. Optics and Precision Engineering,2017,25(5):1135-1141 (in Chinese).
[2] 徐健,孙悦,孙鹏,等.扇出型封装结构可靠性试验方法及验证[J].半导体技术,2018,43(10):787-794.XU J,SUN Y,SUN P,et al.Reliability test methods and verification of the fan-out package [J].Semiconductor Technology,2018,43(10):787-794(in Chinese).
[3] 夏链,贾伟妙,崔鹏,等.基于机器视觉的BGA芯片缺陷检测及其MATLAB实现[J].合肥工业大学学报(自然科学版),2009,32(11):1652-1655.XIA L,JIA W M,CUI P,et al. Defectsinspection and MATLAB realization of BGA chips based on machine vision [J].Journal of Hefei University of Technology,2009,32(11):1652-1655(in Chinese).
[4] 马旭,刘应安,业宁,等.基于核PCA与SVM算法的木材缺陷识别[J].常州大学学报(自然科学版),2017,29(03)::60-68.MA X,LIU Y A,YE N,et al. Application of KPCA and SVM to wood defect recognition[J].Journal of Changzhou University(Natural Science Edition),2017,29(03):60-68 (in Chinese).
[5] 刘晓昱,陈燕宁,李建强,等.适用于高密度封装的失效分析技术及其应用[J].半导体技术,2018,43(4):310-315.LIU X Y,CHEN Y N,LI J Q,et al.Failure analysis technology for high density packaging and its application [J].Semiconductor Technology,2018,43(4):310-315 (in Chinese).
[6] LIU C,QIAO F,YANG X H,et al.Hardware acceleration with pipelined adder for support vector machine classifier [C]// Proceedings of International Conference on Digital Information and Communication Technology and its Applications.Bangkok, Thailand,2014: 13-16.
[7] MANDAL B,SARMA M P,SARMA K K. Design of a systolic array based multiplierless support vector machine classifier[C]// Proceedings of International Conference on Signal Processing and Integrated Networks. Noida, India,2014:35-39.
[8] 王卫兵,白小玲,徐倩.SURF和RANSAC的特征图像匹配[J].哈尔滨理工大学学报,2018,23(1):117-121.WANG W B,BAI X L,XU Q. Features image matching of SURF and RANSAC [J]. Journal of Harbin University of Scienceand Technology,2018,23(1):117-121(in Chinese).
[9] SCHWEITZER H,RUI D,ANDERSON R F.A Dual-bound algorithm for very fast and exact template matching [J]. IEEE Transactions on Pattern Analysis & Machine Intelligence,2011,33(3):459-470.
[10] 吴鹏,徐洪玲,宋文龙.结合小波金字塔的快速NCC图像匹配算法[J].哈尔滨工程大学学报,2017,38(5):791-796.WU P,XU H L,SHONG W L. A fast NCC image matching algorithm based on wavelet pyramid search strategy [J]. Journal of Harbin Engineering University,2017,38(5):791-796(in Chinese).
[11] 汪威,何小凡,李浩然,等.一种包装卷材快速在线检测算法[J].包装工程,2018,39(5):146-152.WANG W,HE X F,LI H R,et al. A fast online detection algorithm for packaging coils [J]. Packaging Engineering,2018,39(5):146-152(in Chinese).
[12] 高向东,蓝重洲,陈子琴,等.焊接缺陷磁光成像动态检测与识别[J].光学精密工程,2017,25(5):1135-1141.GAO X D,LAN C Z,CHEN Z Q,et al.Dynamic detection and recognition of welded defects based on magneto-optical imaging [J]. Optics and Precision Engineering,2017,25(5):1135-1141 (in Chinese).
© 2004-2018 中国地质图书馆版权所有 京ICP备05064691号 京公网安备11010802017129号 地址：北京市海淀区学院路29号 邮编：100083 电话：办公室：(+86 10)66554848；文献借阅、咨询服务、科技查新：66554700 |