基于机器视觉的机械测量及识别技术研究  

Research on Mechanical Measure and Recognition System Based on Machine Vision

作　　者：李文锦[1] 吴海彬[1] 何祖恩[1] 

机构地区：[1]福州大学机械工程及自动化学院,福建福州350002

出　　处：《机床与液压》2010年第1期18-21,115,共5页Machine Tool & Hydraulics

基　　金：福建省自然科学基金资助项目(A0610010)

摘　　要：在自动化生产中,测量技术在产品的检查、装配和品质管理占有重要的地位。其中视觉系统是众多测量工具最具潜力一种。与其他系统相比,视觉系统的最主要优点是高速、高精度且能够方便的调整测量范围。提出了一种基于机器视觉的测量和识别系统。首先使用张氏算法对崎变的图像进行校正,再利用模板匹配和模糊聚类算法对图像进行处理,以获得具体的尺寸参数。试验结果表明该系统能够快速有效地对工件进行测量、具有高的工程应用价值。In automated manufacturing, measurement is important in inspection, assembly and quality assurance of product. One of the most desirable measurement tools is vision system. The main advantages of vision system are high speed, high accuracy and easily modlfing measuring range. A measure and recognition system based on machine vision was proposed. The distortion image was corrected using the algorithm model of zhang. The image was processed using the template matching algorithm and the fuzzy clustering algorithm to obtain the specific size parameters. The experimental results show that this system can be used to recognize the feature and measure the size of parts rapidly and effectively.

关 键 词：标定 模板匹配 OPENCV 模糊聚类 

分 类 号：TP216[自动化与计算机技术—检测技术与自动化装置]