摘要
在PCB的缺陷检测中,基于机器视觉的检测方法应用很广。而该方法主要面对的问题是效率不高。为了解决这个问题,提高检测效率,在具体的算法实现中抛弃了传统的全局阈值分割方法,采用局部阈值分割方法。同时通过选择适合PCB缺陷检测的数学形态运算的结构元素来对PCB图像进行形态滤波,滤波之后再采用Sobel算子来获取PCB的边缘信息。最后对相关算法进行了仿真分析,从仿真结果来看,基本上达到了预期的效果,具有一定的应用前景。
Machine vision-based method is widely used in defect detection of PCB,the main problem of which is low efficiency.In order to solve this problem and improve the detection efficiency,the local threshold segmentation method is adopted instead of the traditional global threshold segmentation method.At the same time,the structural elements of mathematical morphology operation suitable for PCB defect detection are chosen to filter the PCB image.After filtering,Sobel operator is used to get the edge information of PCB.Finally,the related algorithms are simulated and analyzed.The simulation results show that it basically achieves the desired effect and has a certain application prospect.
作者
李世文
LI Shiwen(Heyuan Vocational and Technical College,Heyuan Guangdong 517000,China)
出处
《顺德职业技术学院学报》
2019年第2期9-12,共4页
Journal of Shunde Polytechnic
关键词
PCB图像
局部阈值分割
边缘检测
PCB image
local threshold segmentation
edge detection
