基于改进扩散模型的磁瓦表面缺陷检测方法
Surface defects enhancement algorithm of magnetic tile based on improved diffusion model
张墩利 1周国栋2
作者信息
- 1. 湖南开放大学智能制造学院,湖南长沙 410004
- 2. 湖南开放大学智能制造学院,湖南长沙 410004;中南大学机电工程学院,湖南长沙 410083
- 折叠
摘要
针对电机磁瓦图像对比度低,噪声严重,存在亮条纹干扰,表面缺陷检测困难的问题,提出一种具有亮区抑制功能的各向异性扩散模型.首先设计出亮区特征描述算子用来区分缺陷和干扰,再构造出新的扩散系数函数.实验结果表明,相比同类算法,该模型在背景平滑、边缘检测、图像分割和缺陷识别上都有明显优势,对气孔和裂纹缺陷的检测准确率分别达到 95%和 89%.该研究有效增强磁瓦的低对比度图像,提高缺陷检测精度,具有较高的工程应用潜力.
Abstract
It is difficult to detect the surface defects of the motor magnetic tile,because the image contrast is low,the noise is serious,and there are bright stripes.An anisotropic diffusion model with bright region suppression function is proposed.First,a bright region feature description operator is designed to distinguish defects and interference,and then a new diffusion coefficient function is constructed.The experimental results show that compared with similar algorithms,the model has obvious advantages in background smoothing,edge detection,image segmentation and defect recognition.The detection precision of blowhole and crack defects can reach 95%and 89%respectively.This research effectively enhances the low contrast image of the magnetic tile,improves the defect detection precision,and has high engineering application potential.
关键词
图像处理/亮区特征/自适应扩散模型/磁瓦表面缺陷Key words
image processing/bright area features/adaptive diffusion model/surface defect of magnetic tile引用本文复制引用
基金项目
湖南省教育厅科研项目(22C0971)
湖南省教育厅科研项目(22C0972)
2023年湖南省职业院校教育教学改革研究项目(ZJGB2023381)
湖南开放大学重点课题(XDK-2023-A-3)
出版年
2024
NETL
NSTL
万方数据