基于机器视觉的铸坯表面缺陷检测系统的研制  

Design and implementation of machine vision based surface defect inspecting system

作　　者：吴晓鹏[1] 林介邦[1] 唐辉[1] 钟园园[1] 罗祥英[1] 

机构地区：[1]武钢计控公司,湖北武汉430080

出　　处：《武钢技术》2010年第1期49-53,共5页Wisco Technology

基　　金：国家"863"项目资助(2006AA040307)

摘　　要：钢板作为钢铁工业的主要产品形式之一,已成为汽车、机械制造、化工、航空、航天和造船等工业不可缺少的原材料,其表面质量的优劣将直接影响最终产品的性能和质量。针对目前国内钢板表面缺陷检测方法比较落后、检测效果较差的情况,提出铸坯表面缺陷检测系统的设计与实现方案。系统以计算机视觉理论为检测原理,在现有技术基础上,借助模式识别理论,以模块化为设计思想,通过大量的实验和图像算法仿真,以现有的图像处理理论为基础,设计适合铸坯表面缺陷检测的算法。As one of the major forms of products in steel industry, steel sheet has now become a kind of indispensable material for many industries such as automobile, mechanical manufacturing, chemistry, aviation, spaceflight, ship building, etc. Its surface quality could directly affect performance and quality of the final product. In light of the fact that the methods of surface defect detection for steel in China relatively lag behind and the results of check and inspect in are not so satisfactory the design and implementa- tion scheme of a surface defect detection system for slab is proposed. In accordance to the vision principle of the computer and by means of a great number of experiments and image algorithm simulation an algorithm suitable for detection of the surface defects of the slab is designed out on the basis of the current image disposal theory.

关 键 词：机器视觉 表面缺陷 图像处理 缺陷识别 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术] TF777.1[自动化与计算机技术—计算机科学与技术]