基于机器视觉的药品缺陷检测工站设计与优化

药品缺陷检测是药品生产加工过程中的重要环节,研究药品缺陷检测技术能够有效减少药企生产的压力,促进医药行业的发展。针对目前药品缺陷检测分类技术的研究现状,对国内外已经研究出的药品缺陷检测技术进行分析,发现目前能够应用到实际生产中的技术还不够成熟。提出一种基于机器视觉的药品缺陷检测工站,能够实时完成药品夹层、划痕、斑点和缺损4类缺陷的检测,检测精度最高可达到98.7%,100粒药品的平均检测时间只有15.5 ms,能满足药企的实时生产需求。

Drug defect detection is an important link in the process of drug production and processing.Research on drug defect detection technology can effectively reduce the production pressure of pharmaceutical companies and promote the development of the pharmaceutical industry.In view of the current research status of drug defect detection classification technology,this paper analyzes the drug defect detection technology that has been developed at home and abroad,and finds that the technology that can be applied to actual production is not mature enough.A drug defect detection station based on machine vision is proposed,which can complete the detection of four kinds of defects,namely,drug layers,scratches,spots and defects in real time,with the detection accuracy up to 98.7%,and the average detection time of 100 drugs is only 15.5 ms,which can meet the real-time production needs of pharmaceutical companies.