基于图象处理的冷轧带钢表面缺陷在线检测技术

对光在不同钢板表面的反射性质进行了研究,在此基础上,提出了“明场方式”和“暗场方式”两种缺隐检测方式,“明场方式”可用于检测普碳钢表面的二维和三维缺陷,“暗场方式”可用于检测不锈钢表面的三维缺陷。对缺隐检测算法的流程进行了研究,提出了“实时处理”和“准时处理”两种数据处理方式,这两种方式应用于缺隐检测过程的不同步骤,以保证缺陷检测算法的实时性。

ON-LINE INSPECTION OF SURFACE DEFECTS OF COLD ROLLED STRIPS BASED ON IMAGE PROCESSING

The light reflectivity of different steel surfaces has been investigated.Two methods of surface defect detection are proposed.One is "bright-field detection",which can be used to detect two-dimensional and three dimensional surface defects of common carbon steels.The other is "dark-field detection",which can be used to detect three-dimensional surface defects of stainless steels.The algorithm of defect detection has been studied.Two ways of data processing are presented.One is"real-time processing",the other is "just-in-time processing".Different ways are used in different steps of defect detection,to meet real-time requirement for defect detection.