首页 > 论文 > 激光与光电子学进展 > 56卷 > 21期(pp:211006--1)

结合信息熵与低秩张量分析的金属零件破损检测

Damage Detection of Metal Parts by Combining Information Entropy and Low-Rank Tensor Analysis

  • 摘要
  • 论文信息
  • 参考文献
  • 被引情况
  • PDF全文
分享:

摘要

针对当前金属零件破损处识别研究中自动化程度和识别精度较低等问题,提出一种结合信息熵与低秩张量的金属破损处检测算法。首先,运用差值法、中值滤波和傅里叶滤波等方法对图像进行去噪处理;其次,根据金属零件破损处与其邻域明显的差异性,采用信息熵边缘检测法获取边缘信息;最后,运用低秩张量分析差熵和权差熵矩阵以提取破损处,并与其他算法的结果进行对比分析。实验结果表明,本文算法能够有效并快速地识别金属破损处,检测结果噪声点较少,且该算法的有效精度高于80%,优于传统算法且具有较好的稳健性。

Abstract

This study proposes an algorithm for detecting metal damage in combination with information entropy and low-rank tensor analysis to address the problems of low automation degree and recognition accuracy in the research of damage identification of metal parts. First, the image is denoised using the difference method, median filtering, and Fourier filtering. Second, according to the obvious difference between the damage of the metal part and its surroundings, the information entropy edge detection is used to obtain the edge information. At last, the low-rank tensor method is used to analyze the difference entropy and the weight entropy matrix to extract damage, and it is compared with other algorithms. The experimental results show that the algorithm can effectively and quickly identify metal damage with few noise points. The effective accuracy of the algorithm is higher than 80% with good robustness, which is higher than that of traditional algorithms.

中国激光微信矩阵
补充资料

中图分类号:TP391

DOI:10.3788/LOP56.211006

所属栏目:图像处理

基金项目:国家自然科学基金、江西省自然科学基金;

收稿日期:2019-03-29

修改稿日期:2019-05-05

网络出版日期:2019-11-01

作者单位    点击查看

杨鹏:江西理工大学建筑与测绘工程学院, 江西 赣州 341000
刘德儿:江西理工大学建筑与测绘工程学院, 江西 赣州 341000
李瑞雪:江西理工大学建筑与测绘工程学院, 江西 赣州 341000
刘靖钰:江西理工大学建筑与测绘工程学院, 江西 赣州 341000
张荷苑:成都大学中国-东盟艺术学院, 四川 成都 610106

联系人作者:刘德儿(landserver@163.com)

备注:国家自然科学基金、江西省自然科学基金;

【1】Liu Y, Li Y J and Zhang K. A method of multi-pixels edge detecting of image. Acta Photonica Sinica. 36(2), 380-384(2007).
刘煜, 李言俊, 张科. 一种多像素图像边缘提取方法. 光子学报. 36(2), 380-384(2007).

【2】Li T T, Yang F and Xu X L. Method of large-scale measurement based on multi-vision line structured light sensor. Chinese Journal of Lasers. 44(11), (2017).
李涛涛, 杨峰, 许献磊. 基于多视觉线结构光传感器的大尺度测量新方法. 中国激光. 44(11), (2017).

【3】Hu R W, Zhang X R, Yang L F et al. Trademark pattern tilt correction based on Fourier and Hough transform. Light Industry Machinery. 36(1), 62-65(2018).
胡仁伟, 张希仁, 杨立峰 等. 基于傅里叶变换和Hough变换的商标图案倾斜校正. 轻工机械. 36(1), 62-65(2018).

【4】Liu T T, Wang P G and Zhang N. Subpixel defect detection of highly reflective workpieces based on Zernike-moments. Laser & Optoelectronics Progress. 56(12), (2019).
刘婷婷, 王培光, 张娜. 基于Zernike矩亚像素的高反光金属工件缺陷检测. 激光与光电子学进展. 56(12), (2019).

【5】Li Z H, Zhang L and Yan J H. Research on image edge detection algorithm for pipeline corrosion visual measurement. Journal of Electronic Measurement and Instrumentation. 31(11), 1788-1795(2017).
李忠虎, 张琳, 闫俊红. 管道腐蚀视觉测量图像边缘检测算法研究. 电子测量与仪器学报. 31(11), 1788-1795(2017).

【6】Li X L, Li F, Zhao R et al. Non-threshold windowed Fourier filter algorithm. Acta Photonica Sinica. 43(9), (2014).
李兴龙, 李峰, 赵冉 等. 无阈值窗口傅里叶变换滤波法. 光子学报. 43(9), (2014).

【7】Guo J and Li Z. An edge extraction algorithm based on ICA threshold optimization and information entropy. Journal of Southwest University(Natural Science). 40(9), 150-155(2018).
郭健, 李智. 基于ICA阈值优化耦合信息熵的边缘提取算法. 西南大学学报(自然科学版). 40(9), 150-155(2018).

【8】Jia Y, Wang R B, Yu T H et al. Linear lane mark identification and track method based on entropy maximization edge extraction. Journal of Jilin University(Engineering and Technology Edition). 35(4), 420-425(2005).
贾阳, 王荣本, 余天洪 等. 基于熵最大化边缘提取的直线型车道标识线识别及跟踪方法. 吉林大学学报(工学版). 35(4), 420-425(2005).

【9】Chen G F, Guan G Y and Wei X. Online stamping parts surface defects detection based on machine vision. Laser & Optoelectronics Progress. 55(1), (2018).
陈广锋, 管观洋, 魏鑫. 基于机器视觉的冲压件表面缺陷在线检测研究. 激光与光电子学进展. 55(1), (2018).

【10】Ren K Q and Zhang J R. Extraction of plant leaf vein edges based on fuzzy enhancement and improved Canny. Journal of Optoelectronics·Laser. 29(11), 1251-1258(2018).
任克强, 张静然. 融合模糊增强与改进Canny的植物叶脉边缘提取. 光电子·激光. 29(11), 1251-1258(2018).

【11】Chen Z, Wang B and Zhang L M. Dimensionality reduction and classification based on lower rank tensor analysis for hyperspectral imagery. Journal of Infrared and Millimeter Waves. 32(6), 569-575(2013).
陈昭, 王斌, 张立明. 基于低秩张量分析的高光谱图像降维与分类. 红外与毫米波学报. 32(6), 569-575(2013).

【12】Yang F F and Chen X H. Image edge detection using new weighted entropy minimal spanning tree algorithm. Computer Engineering and Applications. 45(10), 182-183, 198(2009).
杨方方, 陈秀宏. 最小加权熵支撑树图像边缘提取方法. 计算机工程与应用. 45(10), 182-183, 198(2009).

【13】Guo M, Hu L L and Zhao J T. Surface defect detection method of ceramic bowl based on Kirsch and Canny operator. Acta Optica Sinica. 36(9), (2016).
郭萌, 胡辽林, 赵江涛. 基于Kirsch和Canny算子的陶瓷碗表面缺陷检测方法. 光学学报. 36(9), (2016).

【14】Oram J J. McWilliams J C, Stolzenbach K D. Gradient-based edge detection and feature classification of sea-surface images of the Southern California Bight. Remote Sensing of Environment. 112(5), 2397-2415(2008).

【15】Liu Q, Zeng X H, Wang Z H et al. Edge detection by mathematical morphology filtering about quantum superposition state and entropy. Application Research of Computers. 29(6), 2387-2389(2012).
刘清, 曾小荟, 王忠华 等. 量子叠加态和信息熵的形态边缘提取算法. 计算机应用研究. 29(6), 2387-2389(2012).

【16】Jia D, Meng X F, Meng L et al. Image edge extraction combined with a Gaussian weighted distance graph. Journal of Image and Graphics. 19(1), 62-68(2014).
贾迪, 孟祥福, 孟琭 等. 结合高斯加权距离图的图像边缘提取. 中国图象图形学报. 19(1), 62-68(2014).

【17】Cuan Y and Zhao Y. Sub-pixel edge detection of image based on weighted degree of grey entropy. Journal of Northwest University(Natural Science Edition). 45(3), 384-388(2015).
爨莹, 赵洋. 灰熵加权关联分析的亚像素边缘提取算法. 西北大学学报(自然科学版). 45(3), 384-388(2015).

【18】Zhao G, Lin L, Tang Y D et al. Disparity map generation with tensor analysis. Journal of Image and Graphics. 18(10), 1307-1314(2013).
赵戈, 蔺蘭, 唐延东 等. 张量分析在视差图生成中的应用. 中国图象图形学报. 18(10), 1307-1314(2013).

【19】Chen S C, Dai H Y, Wang C et al. Method for filtering dense noise from laser scanning data. Laser & Optoelectronics Progress. 56(6), (2019).
陈世超, 戴华阳, 王成 等. 激光扫描数据的密集噪声剔除方法. 激光与光电子学进展. 56(6), (2019).

引用该论文

Yang Peng,Liu Deer,Li Ruixue,Liu Jingyu,Zhang Heyuan. Damage Detection of Metal Parts by Combining Information Entropy and Low-Rank Tensor Analysis[J]. Laser & Optoelectronics Progress, 2019, 56(21): 211006

杨鹏,刘德儿,李瑞雪,刘靖钰,张荷苑. 结合信息熵与低秩张量分析的金属零件破损检测[J]. 激光与光电子学进展, 2019, 56(21): 211006

您的浏览器不支持PDF插件,请使用最新的(Chrome/Fire Fox等)浏览器.或者您还可以点击此处下载该论文PDF