###

计算机系统应用英文版:2022,31(10):184-190

View/Add Comment 过刊浏览高级检索 HTML

←前一篇 | 后一篇→

码上扫一扫！

下载全文

基于背景差分与最大熵的轨面缺陷分割

王国伟^1,2, 陈光武^3,2, 魏宗寿^1,2

(1.兰州交通大学光电技术与智能控制教育部重点实验室, 兰州 730070;2.甘肃省高原交通信息工程及控制重点实验室, 兰州 730070;3.兰州交通大学自动化与电气工程学院, 兰州 730070)

Rail Surface Defect Segmentation Based on Background Difference and Maximum Entropy

WANG Guo-Wei^1,2, CHEN Guang-Wu^3,2, WEI Zong-Shou^1,2

(1.Key Laboratory of Opt-electonic Technology and Intelligent Control of Ministry of Education, Lanzhou Jiaotong University, Lanzhou 730070, China;2.Gansu Provincial Key Laboratory of Traffic Information Engineering and Control, Lanzhou 730070, China;3.School of Automation & Electrical Engineering, Lanzhou Jiaotong University, Lanzhou 730070, China)

摘要

图/表

参考文献

相似文献

本文已被：浏览 624次下载 1343次
Received:November 09, 2021 Revised:December 17, 2021

中文摘要: 为了提高钢轨表面缺陷检测的效率和准确率, 提出了一种基于背景差分与最大熵的轨面缺陷检测算法. 首先建立钢轨图像背景模型并将原图像与背景图进行差分操作, 以此来避免光照变化和反射不均的影响, 更准确地突出缺陷区域; 然后将改进的遗传算法与最大熵值法相结合来寻找最佳分割阈值并对差分图进行二值化, 通过结合改进遗传算法加快了最大熵值法的运算速度; 最后对二值图进行滤波操作, 完成钢轨表面缺陷的分割. 仿真结果表明该方法能够更加快速准确地分割出缺陷, 精确率、召回率和正确率分别达88.6%、93.4%和90.6%.

中文关键词: 缺陷检测背景差分最大熵轨面改进遗传算法图像分割

Abstract:To improve the efficiency and accuracy of rail surface defect detection, a rail surface defect detection algorithm based on background difference and maximum entropy is proposed. Firstly, the background model of the rail images is built, and the original images are differentiated from the background images to avoid the influence of illumination change and uneven reflection and accurately highlight the defect area. Then, the improved genetic algorithm is combined with the maximum entropy method to seek the best segmentation threshold and binarize the difference graph. The operational speed of the maximum entropy method is accelerated by the improved genetic algorithm. Finally, the binary images are filtered to complete the segmentation of rail surface defects. The simulations indicate that this method can segment defects quickly and accurately, and the precision, recall, and accuracy are 88.6%, 93.4%, and 90.6%, respectively.

keywords: defect detection background difference maximum entropy rail surface improved genetic algorithm image segmentation

文章编号： 中图分类号： 文献标志码：

基金项目:国家自然科学基金(61863024); 甘肃省科技引导计划(2020-61)

引用文本：
王国伟,陈光武,魏宗寿.基于背景差分与最大熵的轨面缺陷分割.计算机系统应用,2022,31(10):184-190
WANG Guo-Wei,CHEN Guang-Wu,WEI Zong-Shou.Rail Surface Defect Segmentation Based on Background Difference and Maximum Entropy.COMPUTER SYSTEMS APPLICATIONS,2022,31(10):184-190

Author Name	Affiliation	E-mail
WANG Guo-Wei	Key Laboratory of Opt-electonic Technology and Intelligent Control of Ministry of Education, Lanzhou Jiaotong University, Lanzhou 730070, China Gansu Provincial Key Laboratory of Traffic Information Engineering and Control, Lanzhou 730070, China
CHEN Guang-Wu	School of Automation & Electrical Engineering, Lanzhou Jiaotong University, Lanzhou 730070, China Gansu Provincial Key Laboratory of Traffic Information Engineering and Control, Lanzhou 730070, China	cgwyjh1976@126.com
WEI Zong-Shou	Key Laboratory of Opt-electonic Technology and Intelligent Control of Ministry of Education, Lanzhou Jiaotong University, Lanzhou 730070, China Gansu Provincial Key Laboratory of Traffic Information Engineering and Control, Lanzhou 730070, China

Author Name	Affiliation	E-mail
WANG Guo-Wei	Key Laboratory of Opt-electonic Technology and Intelligent Control of Ministry of Education, Lanzhou Jiaotong University, Lanzhou 730070, China Gansu Provincial Key Laboratory of Traffic Information Engineering and Control, Lanzhou 730070, China
CHEN Guang-Wu	School of Automation & Electrical Engineering, Lanzhou Jiaotong University, Lanzhou 730070, China Gansu Provincial Key Laboratory of Traffic Information Engineering and Control, Lanzhou 730070, China	cgwyjh1976@126.com
WEI Zong-Shou	Key Laboratory of Opt-electonic Technology and Intelligent Control of Ministry of Education, Lanzhou Jiaotong University, Lanzhou 730070, China Gansu Provincial Key Laboratory of Traffic Information Engineering and Control, Lanzhou 730070, China