基于视觉传感器的输液中异物检测系统设计  

Design of particles detection system for pharmaceutical liquor based on vision sensor

作　　者：杨福刚[1,2] 

机构地区：[1]山东工商学院信息与电子工程学院,山东烟台264005 [2]山东大学控制科学与工程学院,山东济南250061

出　　处：《传感器与微系统》2010年第3期74-76,79,共4页Transducer and Microsystem Technologies

基　　金：国家自然科学基金资助项目(60773053)

摘　　要：为实现输液中异物的在线自动检测,设计了一种基于高性能视觉传感器的液体中微小异物检测系统。针对输液中微小异物的特点,设计了可编程控制的图像采集系统,以获取高质量的原始视觉图像。对采集到的图像通过预处理、特征提取、异物目标识别分类等算法实现了对异物目标的在线检测。实验表明:该系统对输液中粒径大于50μm异物的识别准确率和识别速度均高于熟练灯检工。To detect the possible foreign and particulate matter in pharmaceutical liquor online, a novel particles detection hardware system and image recognition algorithm are developed. According to characteristics of particles in infusion, a programmable control of the image acquisition system aimed to acquire high quality image sequences is designed. Some algorithms, such as image pre-processing, feature extraction, target identification, is carried out to achieve online detection of foreign particles. Experimental results show that the system can effective detects foreign particles whose sizes are bigger than 50 μm in liquor. Its recognition accuracy and detection speed is higher than skilled workers.

关 键 词：微小异物检测 视觉传感器 输液检测 最小二乘支持向量机 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]