基于计算机视觉的蜂窝陶瓷在线检测系统研究  

Research and Development of Honeycomb Ceramics' On-line Automatic Inspection System Based on Computer Vision

作　　者：李颖[1,2] 黄守道[2] 孙洪林[1] 李刚成[1] 

机构地区：[1]湖南信息职业技术学院,长沙410200 [2]湖南大学电气与信息工程学院,长沙410082

出　　处：《计算机测量与控制》2014年第8期2419-2421,共3页Computer Measurement &Control

基　　金：湖南省科技厅资助项目(2012FJ3093)

摘　　要：研发了一种基于计算机视觉的蜂窝陶瓷智能在线检测系统;设计了系统的体系结构,4台高速摄像机在线获取蜂窝陶瓷图像,研究了改进型加权中值滤波处理,论述了基于Fisher评价函数的图像阈值分割算法;最后进行亚像素测量,判断产品尺寸是否在允许范围内,实验验证了系统的有效性和检测算法的可行性,可以很好地代替人工检测。This paper introduce a design of honeycomb ceramics＇ on--line automatic checkout system based on machine vision. The checkout system acquires images of honeycomb ceramics through high--speed video camera. Firstly, the images are processed by using im- proved weighted median filtering. Then, the images run into threshold segmentation on the basis of Fisher criterion function method. Finally, suh--pixel measurement is applied so as to judge whether the product dimension is within the allowed scope. The experiment proves the effectiveness of the system and feasibility of detecting algorithm.

关 键 词：计算机视觉 蜂窝陶瓷 FISHER评价函数 亚像素测量 

分 类 号：TP274[自动化与计算机技术—检测技术与自动化装置]