您好,欢迎来到login_星欧(官方)代理招商直营娱乐!

首页> 《中国测试》期刊 >本期导读>基于改进扩散模型的磁瓦表面缺陷检测方法

基于改进扩散模型的磁瓦表面缺陷检测方法

368    2024-06-26

¥0.50

全文售价

作者:张墩利1, 周国栋1,2

作者单位:1. 湖南开放大学智能制造学院, 湖南 长沙 410004;
2. 中南大学机电工程学院, 湖南 长沙 410083


关键词:图像处理;亮区特征;自适应扩散模型;磁瓦表面缺陷


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。


Surface defects enhancement algorithm of magnetic tile based on improved diffusion model
ZHANG Dunli1, ZHOU Guodong1,2
1. School of Intelligent Manufacturing, Hunan Open University, Changsha 410004, China;
2. College of Mechanical and Electrical Engineering, Central South University, Changsha 410083, China
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.
Keywords: image processing; bright area features; adaptive diffusion model; surface defect of magnetic tile
2024, 50(6):28-34 收稿日期: 2023-02-03;收到修改稿日期: 2023-05-10
基金项目: 湖南省教育厅科研项目(22C0971,22C0972);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)
作者简介: 张墩利(1979-),女,江苏宿迁市人,副教授,硕士,研究方向为无损检测与机器视觉。
参考文献
[1] 文喆皓, 周敏. 基于深度学习的磁瓦表面孔洞和裂纹缺陷识别[J]. 兵器材料科学与工程, 2020, 43(6): 106-112.
WEN Z H,ZHOU M. Recognition of blowholes and cracks on surface of magnetic tile based on deep learning[J]. Ordnance Material Science and Engineering, 2020, 43(6): 106-112.
[2] XIE L, LIN L, YIN M, et al. A novel surface defect inspection algorithm for magnetic tile[J]. Applied Surface Science, 2016, 375: 118-126.
[3] LI XQ J H H, YIN G F. Detection of surface crack defects on ferrite magnetic tile[J]. Ndt & E International, 2016, 62: 6-13.
[4] 华泽锋, 潘孟春, 陈棣湘,等. 发动机叶片微缺陷自动检测系统的设计[J]. 中国测试, 2021, 47(10): 109-113.
HUA Z F, PAN M C, CHEN D X, et al. Design of automatic detection system for micro defects in engine blade[J]. China Measurement & Test, 2021, 47(10): 109-113.
[5] YANG C, LIU P, YIN G, et al. Defect detection in magnetic tile images based on stationary wavelet transform[J]. Ndt & E International, 2016, 83: 78-87.
[6] 朱志勋, 李恒, 赵磊, 等. 基于改进的同态滤波与SMQT相结合的磁瓦表面缺陷图像增强算法研究[J]. 光电子·激光, 2021, 32(8): 818-825.
ZHU Z X, LI H, ZHAO L, et al. Research on image enhancement algorithm of magnetic tile surface defect based on improved homomorphic filtering and SMQT[J]. Journal of Optoelectronics & Laster, 2021, 32(8): 818-825.
[7] 项新建, 李超, 尤钦寅. 基于图像增强的气门弹簧座内壁划痕检测算法[J/OL]. 中国测试: 1-8[2023-02-20]. http://kns.cnki.net/kcms/detail/51.1714.TB.20211201.1245.012.html.
XIANG X J, LI C, YOU Q Y. Valve spring seat’s scratches detection algorithm based on image enhancement[J]. China Measurement and Test,1-8[2023-02-20]. http://kns.cnki.net/kcms/detail/51.1714.TB.20211201.1245.012.html.
[8] 徐佳乐, 黄丹平, 廖世鹏, 等. 基于线扫描技术的轴承表面缺陷检测方法研究[J]. 中国测试, 2022, 48(11): 88-94.
XU J L, HUANG D P, LIAO S P, et al. Study on detection method of bearing surface defect based on line scanning technology[J]. China Measurement and Test, 2022, 48(11): 88-94.
[9] HUANG Y, QIU C, YUAN K. Surface defect saliency of magnetic tile[J]. The Visual Computer, 2020, 36(1): 85-96.
[10] 谢舰, 姚剑敏, 严群, 等. 基于深度学习的磁瓦表面缺陷分割与识别[J]. 液晶与显示, 2021, 36(5): 713-722.
XIE J, YAO J M, YAN Q, et al. Segmentation and recognition of magnetic tile surface defects based on deep learning[J]. Chinese Journal of Liquid Crystals and Displays, 2021, 36(5): 713-722.
[11] 祝礼佳, 刘桂华, 林杰. 基于卷积神经网络的磁瓦表面缺陷识别[J]. 制造业自动化, 2022, 44(3): 48-53.
ZHU L J, LIU G H, LIN J. Recognition of magnetic tile surface defects based on convolution neural network[J]. Manufacturing Automation, 2022, 44(3): 48-53.
[12] PERONA P, MALIK J. Scale-space and edge detection using anisotropic diffusion[J]. IEEE Transactions on pattern analysis and machine intelligence, 1990, 12(7): 629-639.
[13] 张天祥. 各向异性模型图像增强算法的研究与FPGA实现[D]. 太原: 中北大学, 2020.
ZHANG T X. Research and implementation of image enhancement algorithm of anisotropic model based on FPGA [D]. North University of China,2020.
[14] CHAO S M, TSAI D M. An anisotropic diffusion-based defect detection for low-contrast glass substrates[J]. Image and Vision Computing, 2018, 26(2): 187-200.
[15] CHAO S M, TSAI D M. Anisotropic diffusion with generalized diffusion coefficient function for defect detection in low-contrast surface images[J]. Pattern Recognition: The Journal of the Pattern Recognition Society, 2010, 43(5): 1917-1931.
[16] 许翊, 刘学军. 计算机双目视觉中的动态规划立体匹配算法研究[J]. 西南师范大学学报(自然科学版), 2020, 45(9): 118-123.
XU Y, LIU X J. On dynamic programming stereo matching algorithms in computer binocular vision[J]. Journal of Southwest China Normal University(Natural Science Edition), 2020, 45(9): 118-123.