基于机器视觉的液体药品异物检测系统研究

Research on foreign substance detection system for medicinal solution based on machine vision

为实现液体药品异物在线高速高精度检测,设计了一套基于机器视觉的自动化检测系统。本文首先研究了异物检测系统的机械与电气控制系统结构,开发了面向医药生产线的图像获取装置。然后根据药液内异物运动轨迹连续性的特点,提出了基于序列图像的检测跟踪识别算法。最后,选择100 m l玻璃瓶装10%葡萄糖和0.9%氯化钠药品为对象进行测试,实验表明:本文设计的检测系统能很好地满足医药生产线的需求,检测分辨率达到10μm,准确率近95%。

To detect foreign substance in medicinal solution with high speed and high precision, an automatic detection system based on machine vision is presented. Firstly, the mechanical and electrical control system structures are studied in detail, and the image acquisition device for medicine product line is developed. Secondly, according to the feature that foreign substance moves successively in medicinal solution, an algorithm based on sequence image for foreign detection is proposed. Thirdly, 100 ml 10% dextrose and 0.9 Nacl solution mixed in glass bottle are chosen as the test object, a detection rate of about 95% is experimentally achieved for substances lager than lOum in diameter. ment results demonstrate that the proposed system can satisfy the requirement of the medicine product line.