位置信息约束的SMT料盘X射线图像检测方法

耿磊; 彭晓帅; 肖志涛; 李秀艳; 荣锋; 马潇

doi:10.3788/IRLA201746.0617004

位置信息约束的SMT料盘X射线图像检测方法

doi: 10.3788/IRLA201746.0617004

耿磊^1,2,
彭晓帅^1,2,
肖志涛^1,2, ,,
李秀艳^1,2,
荣锋^1,2,
马潇^1,2

1.
天津市光电检测技术与系统重点实验室,天津 300387;
2.
天津工业大学电子与信息工程学院,天津 300387

基金项目:

国家自然科学基金（61405144）;天津市科技支撑计划重点项目（14ZCZDGX00033）;天津市科技特派员项目（15JCTPJC56300）

详细信息

作者简介:
耿磊(1982-),男,副教授,硕士生导师,主要从事测试测量技术及仪器方面的研究。Email:genglei@tjpu.edu.cn

通讯作者: 肖志涛(1971-),男,教授,博士生导师,主要从事图像处理与模式识别方面的研究。Email:xiaozhitao@tjpu.edu.cn

中图分类号: TP391

Method for detecting the X-Ray images of SMT materials plates based on the constraints of position information

Geng Lei^1,2,
Peng Xiaoshuai^1,2,
Xiao Zhitao^{1,2
, ,},
Li Xiuyan^1,2,
Rong Feng^1,2,
Ma Xiao^1,2

1.
Tianjin Key Laboratory of Optoelectronic Detection Technology and System,Tianjin 300387,China;
2.
School of Electronics and Information Engineering,Tianjin Polytechnic University,Tianjin 300387,China

摘要: SMT封装物料盘的X射线透视图像发生局部粘连，导致分割准确性降低影响物料的检测与计数统计。提出了基于位置信息约束的分割检测方法，利用器件位置信息对分割区域进行约束提高分割与检测的准确率。首先依据元器件呈螺旋状排列规则，拟合物料盘中心点并计算最内环排列中起点器件位置信息；然后基于中心点与各元器件的位置约束模型，进行法向位置信息与先验位置信息双重约束，对目标器件所在区域进行限定；最后划分分割界限，完成对粘连目标的分割和对元器件的检测与统计。实验结果表明：该方法能够提高物料盘X射线透视图像粘连区域分割与检测的准确率，在有效像元素9 216 pixel，细节解析度110 1p/cm成像环境之下，对不同规格物料盘进行实测，检测误差率控制在0.15%之内。
- X射线透视图像 /
- 粘连 /
- 计数统计 /
- 分割检测 /
- 位置信息约束
Abstract: The local adhesion in the X-Ray images of SMT material plates has negative effects on the accuracy of counting and detection for components. A method based on the constraints of position information was proposed, which was used to improve the accuracy of segmentation and detection with the position information between components. Firstly, the center point and the starting components arranged in the inner ring were fit out on the basis of the components in a spiral arrangement rule. Then the dual constraints of normal position and priori position, which were based on the constraint model between the center point and different components, were finished to limit the region of target device. Finally, the segmentation for conglutination between components was completed by dividing the boundaries between components. Experimental results show that this method can improve the accuracy of the result of segmentation and detection. The detection error rate tested on different specifications material plates is controlled within 0.15% under the experimental conditions of 9 216 pixels effective image element and detail resolution of 110 1p/cm.
- X-Ray images /
- adhesion /
- counting statistics /
- segmentation and detection /
- constraints of position information

[1]	Lewiecki E M, Laster A J. Clinical review: clinical applications of vertebral fracture assessment by dual energy X-Ray absorptiometry [J]. The Journal of Clinical Endocrinology Metabolism, 2006, 91(11): 4215-4222.
[2]	Mao Haifeng. The applications of AOI in SMT detection [J]. Science and Technology Information, 2010, 27(5): 57-58. (in Chinese)
[3]	Min Sizong. The applications of digital image processing in SMT detection[J]. Computer and Network, 2010, 24: 247-248. (in Chinese)
[4]	Erik M. Cell segmentation：50 years down the road [J]. Signal Processing Magazine, 2012, 29(5): 140-145.
[5]	Lei Yan, Cheol-Woo Park, Sang-Ryong Lee, et al. Separation algorithm for touching grain kernels based on contour segments and ellipse fitting[J]. Zhejiang Univ-SciC(Comput Electron), 2011, 12(1): 54-61.
[6]	Vantaram S R, Saber E. Survey of contemporary trends in color image segmentation [J]. Journal of Electronic Imaging, 2012, 21(4): 040901.
[7]	Roerdink Jbtm, Meijster A. The watershed transform： Definitions, algorithms and parallelization strategies [J]. Fundamenta Informaticae, 2000, 41(1): 187-228．
[8]	Farhan M, Yli-Harja O, Niemist A. A novel method forsplitting clumps of convex objects incorporating image intensity and using rectangular window-based concavity point-pair search[J]. Pattern Recognition, 2013, 46(3): 741-751.
[9]	Ji Zexuan, Pan Yu, Chen Qiang, et al. Natural image segmentation algorithm with unsupervised FCM[J]. Journal of Image and Graphics, 2011, 16(5): 773-783. (in Chinese)
[10]	Sun Zhaolei, Hui Bin, Qin Mofan, et al. Object detection method based on saliencymeasure for infrared radiation image [J]. Infrared and Laser Engineering, 2015, 44(9): 2633-2637. (in Chinese)
[11]	Wang Dongdong, Zhang Wei, Jin Guofeng, et al. Application of cusp catastrophic theory in image segmentation of infrared thermal waving inspection[J]. Infrared and Laser Engineering, 2014, 43(3): 1009-1015. (in Chinese)
[12]	Zhang Zhongyu, Jiao Shuhong. Infrared hip target detection methods based on multiple feature fusion [J]. Infrared and Laser Engineering, 2015, 44(S): 29-34. (in Chinese)
[13]	Zhao Qing. K-means efficient algorithm and research on hadoop platform[D]. Xi'an: Xidian University, 2014. (in Chinese)
[14]	Faustion G M, Gattass M, Rehen S. Automatic embryonicstem cell detection and counting method in fluorescence icroscopy images[J]. Transactions on Information Theory, 2012, 58(2): 1094-1121.
[15]	Song Hong, Wang Yong, Huang Xiaochuan, et al. A dynamic adaptive region growing segmentation algorithm for tumor of liver CT images[J]. Transactions of Beijing Institute of Technology, 2014, 43(1): 72-76. (in Chinese)
[16]	AllaouiA E, Nasri M. Medical image segmentation by marker-controlled watershed and mathematical morphology[J]. International Journal of Multimedia its Applications, 2012, 4(3): 151-158.
[17]	Zhang Qian, He Jianfeng, Ma Lei. The study of image segmentation based on the combination of the wavelet multi-scale edge detection and the entropy iterative threshold selection[J]. Chinese Journal of Biomedical Engineering, 2013, 22(4): 154-160. (in Chinese)

[1]	柯岩, 傅云, 周玮珠, 朱伟东. 基于Transformer的复合材料多源图像实例分割网络 . 红外与激光工程, 2023, 52(2): 20220338-1-20220338-13. doi: 10.3788/IRLA20220338
[2]	惠俊, 柴洪洲, 向民志, 杜祯强, 靳凯迪. 量子增强星载光子计数激光雷达阈值检测性能 . 红外与激光工程, 2023, 52(4): 20220469-1-20220469-11. doi: 10.3788/IRLA20220469
[3]	林森, 赵振禹, 任晓奎, 陶志勇. 基于语义信息补偿全局特征的物体点云分类分割 . 红外与激光工程, 2022, 51(8): 20210702-1-20210702-12. doi: 10.3788/IRLA20210702
[4]	韦敏习, 尚万里, 侯立飞, 孙奥, 车兴森, 杨国洪. 高精度X射线柱面弯晶检测方法 . 红外与激光工程, 2022, 51(10): 20211121-1-20211121-5. doi: 10.3788/IRLA20211121
[5]	于洋, 张红刚, 高军科, 王建刚. 光电平台角位置信息摩擦观测补偿技术 . 红外与激光工程, 2022, 51(5): 20210557-1-20210557-8. doi: 10.3788/IRLA20210557
[6]	缪立军, 闫景涛, 胡慧珠, 应光耀, 黄腾超, 车双良, 舒晓武. 光阱中微粒位置高精度检测技术 . 红外与激光工程, 2019, 48(12): 1213001-1213001(7). doi: 10.3788/IRLA201948.1213001
[7]	吴朝, 魏文彬, 高昆, 田扬超. 快速高能X射线光栅相衬成像 . 红外与激光工程, 2019, 48(8): 825004-0825004(5). doi: 10.3788/IRLA201948.0825004
[8]	汪子君, 邱俨睿, 杨宏霄, 孙磊. 基于鲁棒Otsu的红外无损检测缺陷分割算法 . 红外与激光工程, 2019, 48(2): 204004-0204004(9). doi: 10.3788/IRLA201948.0204004
[9]	刘娜, 沈正祥, 马彬, 魏振博, 徐旭东, 王占山. 圆锥近似Wolter-I型X射线望远镜用柱面反射镜面形误差检测方法 . 红外与激光工程, 2018, 47(4): 417001-0417001(7). doi: 10.3788/IRLA201847.0417001
[10]	顾礼, 宗方轲, 李翔, 周军兰, 杨勤劳, 郭宝平. 用于激光聚变的X射线条纹相机阴极检测系统 . 红外与激光工程, 2018, 47(8): 817002-0817002(5). doi: 10.3788/IRLA201847.0817002
[11]	荣锋, 梁莹, 杨亚东, 马雪皓. X射线光栅相衬成像的仿真 . 红外与激光工程, 2017, 46(12): 1220002-1220002(7). doi: 10.3788/IRLA201746.1220002
[12]	齐楠楠, 姜鹏飞, 李彦胜, 谭毅华. 基于视觉显著性和目标置信度的红外车辆检测技术 . 红外与激光工程, 2017, 46(6): 604005-0604005(9). doi: 10.3788/IRLA201746.0604005
[13]	张玲, 沈正祥, 刘娜, 余俊, 王占山. 基于多元约束的小型软X射线偏振望远镜光学设计及优化 . 红外与激光工程, 2017, 46(7): 718002-0718002(7). doi: 10.3788/IRLA201746.0718002
[14]	吴佳彬, 陈云善, 高世杰, 吴志勇. 高精度近红外光斑位置检测模型研究 . 红外与激光工程, 2016, 45(7): 717001-0717001(7). doi: 10.3788/IRLA201645.0717001
[15]	许家林, 王晓东, 李丙玉, 王鹤, 孙强. 基于DMD的红外场景模拟器图像数据传输和分割存储方法 . 红外与激光工程, 2015, 44(9): 2622-2626.
[16]	薛模根, 周浦城, 刘存超. 夜视图像局部颜色传递算法 . 红外与激光工程, 2015, 44(2): 781-785.
[17]	郭靖, 江洁, 曹世翔. 水平集分层分割遥感图像中的建筑物 . 红外与激光工程, 2014, 43(4): 1332-1337.
[18]	严飞, 侯晴宇. 基于多元统计特性异常的盲元检测算法 . 红外与激光工程, 2014, 43(2): 454-457.
[19]	刘松林, 牛照东, 陈曾平. 交叉熵约束的红外图像最小错误阈值分割 . 红外与激光工程, 2014, 43(3): 979-984.
[20]	王冬冬, 张炜, 金国锋, 杨正伟, 田干. 尖点突变理论在红外热波检测图像分割中的应用 . 红外与激光工程, 2014, 43(3): 1009-1015.

点击查看大图

计量

文章访问数: 426
HTML全文浏览量: 65
PDF下载量: 60
被引次数: 0

姓名
邮箱
手机号码
标题
留言内容
验证码

留言板

位置信息约束的SMT料盘X射线图像检测方法

doi: 10.3788/IRLA201746.0617004

作者简介:
耿磊(1982-),男,副教授,硕士生导师,主要从事测试测量技术及仪器方面的研究。Email:genglei@tjpu.edu.cn

通讯作者: 肖志涛(1971-),男,教授,博士生导师,主要从事图像处理与模式识别方面的研究。Email:xiaozhitao@tjpu.edu.cn

Method for detecting the X-Ray images of SMT materials plates based on the constraints of position information

计量

位置信息约束的SMT料盘X射线图像检测方法

doi: 10.3788/IRLA201746.0617004

1. 天津市光电检测技术与系统重点实验室,天津 300387;

2. 天津工业大学电子与信息工程学院,天津 300387

作者简介:
耿磊(1982-),男,副教授,硕士生导师,主要从事测试测量技术及仪器方面的研究。Email:genglei@tjpu.edu.cn

通讯作者: 肖志涛(1971-),男,教授,博士生导师,主要从事图像处理与模式识别方面的研究。Email:xiaozhitao@tjpu.edu.cn

English Abstract

Method for detecting the X-Ray images of SMT materials plates based on the constraints of position information

1. Tianjin Key Laboratory of Optoelectronic Detection Technology and System,Tianjin 300387,China;

2. School of Electronics and Information Engineering,Tianjin Polytechnic University,Tianjin 300387,China

全文HTML

目录

留言板

位置信息约束的SMT料盘X射线图像检测方法

doi: 10.3788/IRLA201746.0617004

作者简介: 耿磊(1982-),男,副教授,硕士生导师,主要从事测试测量技术及仪器方面的研究。Email:genglei@tjpu.edu.cn

通讯作者: 肖志涛(1971-),男,教授,博士生导师,主要从事图像处理与模式识别方面的研究。Email:xiaozhitao@tjpu.edu.cn

Method for detecting the X-Ray images of SMT materials plates based on the constraints of position information

计量

出版历程

位置信息约束的SMT料盘X射线图像检测方法

doi: 10.3788/IRLA201746.0617004

1. 天津市光电检测技术与系统重点实验室,天津 300387; 2. 天津工业大学 电子与信息工程学院,天津 300387

作者简介: 耿磊(1982-),男,副教授,硕士生导师,主要从事测试测量技术及仪器方面的研究。Email:genglei@tjpu.edu.cn

通讯作者: 肖志涛(1971-),男,教授,博士生导师,主要从事图像处理与模式识别方面的研究。Email:xiaozhitao@tjpu.edu.cn

English Abstract

Method for detecting the X-Ray images of SMT materials plates based on the constraints of position information

1. Tianjin Key Laboratory of Optoelectronic Detection Technology and System,Tianjin 300387,China; 2. School of Electronics and Information Engineering,Tianjin Polytechnic University,Tianjin 300387,China

全文HTML

目录

作者简介:
耿磊(1982-),男,副教授,硕士生导师,主要从事测试测量技术及仪器方面的研究。Email:genglei@tjpu.edu.cn

1. 天津市光电检测技术与系统重点实验室,天津 300387;

2. 天津工业大学电子与信息工程学院,天津 300387

作者简介:
耿磊(1982-),男,副教授,硕士生导师,主要从事测试测量技术及仪器方面的研究。Email:genglei@tjpu.edu.cn

1. Tianjin Key Laboratory of Optoelectronic Detection Technology and System,Tianjin 300387,China;

2. School of Electronics and Information Engineering,Tianjin Polytechnic University,Tianjin 300387,China