基于形态学滤波的中厚板边部裂纹检测方法  

Plate edge crack detection method based on morphological filter

作　　者：宗德祥[1] 何永辉[1] 张林鹏[2] 彭铁根[1] 

机构地区：[1]宝山钢铁股份有限公司,上海201900 [2]西安交通大学,陕西西安710049

出　　处：《宝钢技术》2014年第3期30-34,共5页Baosteel Technology

摘　　要：介绍了数学形态学的原理和应用,针对中厚板表面图像存在的低对比度、背景复杂和氧化皮干扰等问题,分析表面裂纹的形态特性,提出了基于多重形态滤波和图像块累积直方图分析的表面裂纹在线检测方法。通过与其他形态学方法的对比试验,表明该方法不仅能有效地消除噪音干扰、更为准确地检测裂纹,而且能够满足实际生产的实时性需求。The principle and application of mathematical morphology is introduced, in view of the plate surface image is low contrast, complex background and with iron oxide interference, one solution based on multiple morphology filter and image blocks cumulative histogram analysis is proposed to find the true crack. By comparing with other methods, this method not only can effectively eliminate the noise interference, more accurate detection of cracks, and can meet the real time requirement of actual production.

关 键 词：中厚板 边部裂纹 形态学滤波 图像块分析 缺陷检测 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]