基于小波提升分解的带钢表面缺陷检测  

Strip steel surface defect detection based on wavelet lifting decomposition

作　　者：张勇[1] 管声启[2] 

机构地区：[1]西安工程大学教务处,陕西西安710048 [2]西安工程大学机电工程学院,陕西西安710048

出　　处：《西安工程大学学报》2013年第4期483-487,491,共6页Journal of Xi’an Polytechnic University

摘　　要：针对带钢表面缺陷的特点,提出了一种基于图像处理的快速检测方法.首先,通过分析小波的提升格式,确定了带钢图像的小波提升分解方法.其次,利用DB2小波对带钢图像进行二层提升分解.然后,选取二层水平细节和垂直细节子图进行图像融合.在此基础上,对融合图像进行标准化和维纳滤波.最后通过oust方差法进行分割从而实现对带钢表面缺陷的检测.实验表明,采用此方法能够有效抑制图像背景干扰,实现带钢缺陷的快速检测.Rapid detection method is studied on surface defects of strip.Aiming at the characteristics of strip steel surface defect,a based image processing method is put forward for rapid detection.First of all,the fast wavelet decomposition method is determined through the analysis of the wavelet lifting scheme.Secondly,strip images are decomposed into two layer sub-images using the DBz wavelet.Then,selecting second layer＇s level detail and vertical detail sub-images for image fusion.On this basis,the fusion image is normalized and filtered by Wiener filter.Finally strip surface defect is detected through the oust variance method.Experiments show that this method can effectively suppress the image background interference,and effectively realize the rapid detection of strip steel.

关 键 词：带钢缺陷 快速检测 小波分解 提升格式 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]