基于机器视觉的医用瓶盖质检系统设计

Design of Quality Inspection System for Medical Bottle Caps Based on Machine Vision

为解决医用瓶盖仍然依靠人工方式进行质量检测的不足,基于机器视觉技术,设计开发了一套医用瓶盖高速智能检测系统。首先,系统采用真空吸附技术,使用6台高速工业相机,可对瓶盖图像进行全方位稳定采集;其次,利用区域预测、模板匹配等方式,对不同区域进行快速定位分割,并进行质量检测。大量试验和现场测试表明,系统可对不同瑕疵,如油污、缺口、圆度、高度进行检测。系统稳定可靠,检测速度可达950个/min,剔除准确率达99.99%。

In order to overcome the shortcoming that medical bottle cap still depends on manual inspection,a high speed intelligent testing system for medical bottle cap was designed and developed.Firstly,the system adopted vacuum absorption technology and six high-speed industrial cameras to collect images stably for all sides of the bottle cap.Secondly,using the methods of region prediction and template matching,the different regions were quickly located and segmented,and then the quality detection was carried out.A large number of tests show that the system can detect different defects,such as oil stain,notch,roundness and height.The system is stable and reliable,the detection speed and the removal accuracy rate can achieve to 950/min and 99.99% respectively.