摘要
提出一种基于Zernike矩的亚像素直线检测方法,实现对航空航天薄壁结构件窄间隙焊缝中心线的快速精确提取。将采集到的焊缝图像进行ROI提取计算,以减小需要图像处理的区域,提高图像处理算法的速度;运用高斯滤波处理对其去噪;经过阈值分割后,采用Zernike矩算子检测提取焊缝图像中的焊缝直线,设定阈值过滤掉干扰点;最后进行亚像素细分计算,得出焊缝中心线的精确定位。实验证明,该方法检测精度更高,抗干扰能力强,对图像中直线的残缺部分以及其它共存的非直线结构不敏感,相对不受图像噪声的影响。
A subpixel linear detection method based on Zernike moment is proposed to realize rapid and accurate extraction of the center lines of narrow gap welds in aerospace thin-walled structures.ROI extraction of weld image will be collected to reduce the area of image processing, so as to improve the speed of image processing algorithm.The gaussian filter processing is used for the denoising.After threshold segmentation, the Zernike moment operators are used to detect extract weld lines in the images of the weld and set threshold to filter out noise points.The final calculation of subpixel subdivision is done to get an accurate positioning of the weld centerline.The experimental results show that this method has higher detection accuracy, strong anti-interference ability, and is insensitive to the incomplete part of the straight line, noise and other non-linear structures coexisting in the image.It is relatively immune to the influence of image noise.
作者
刘军
赵剑英
池云
LIU Jun;ZHAO Jianying;CHI Yun(Shenyang Ligong University,Shenyang 110159,China)
出处
《沈阳理工大学学报》
CAS
2021年第4期1-5,10,共6页
Journal of Shenyang Ligong University
基金
辽宁省自然科学基金指导计划(2019-ZD-0251)
国家重点专项(2018YFB1107800)。
