Segmentation and recognition of magnetic tile surface defects based on deep learning

Jian XIE; Jian-min YAO; Qun YAN; Zhi-xian LIN

doi:10.37188/CJLCD.2020-0247

您当前的位置：

首页 >

文章列表页 >

Segmentation and recognition of magnetic tile surface defects based on deep learning

Image Processing | 更新时间：2021-01-21

- Segmentation and recognition of magnetic tile surface defects based on deep learning
- Chinese Journal of Liquid Crystals and Displays Vol. 36, Issue 5, Pages: 713-722(2021)
- 作者机构：
  
  1.福州大学物理与信息工程学院, 福建福州 350108
  2.晋江市博感电子科技有限公司, 福建晋江 362200
- 作者简介：
- 基金信息：
  
  National Key Research and Development Program of China;Open Fund of Guangdong Provincial Key Laboratory of Optical Information Materials and Technology
- DOI：10.37188/CJLCD.2020-0247
  CLC： TP394.1;TH691.9
- Received：24 September 2020，
  
  Revised：28 October 2020，
  
  Published：2021-05
- 稿件说明：
移动端阅览
Jian XIE, Jian-min YAO, Qun YAN, 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.
DOI：

Jian XIE, Jian-min YAO, Qun YAN, 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. DOI： 10.37188/CJLCD.2020-0247.

摘要

为了满足磁瓦生产工业对表面质量检测的高要求，实现磁瓦缺陷自动分割与识别，本文提出了一种基于卷积神经网络的缺陷分割与分类网络。该网络基于U-net架构，通过U-net编码部分提取缺陷的深层特征，并使用该深层特征进行缺陷分类，然后通过解码部分输出分割的缺陷区域。为了解决部分缺陷前景面积占比太小，导致网络难以收敛的问题，通过添加差异系数损失以保证网络持续优化。然后在训练阶段添加多层损失和进行在线数据增强进一步提升了分割精度和分类准确率。实验结果表明，添加辅助损失函数和数据增强后，分割网络能够分割出94.5%标注的缺陷区域，并且对于缺陷分类的准确率能够达到98.9%，满足工业生产的高精度要求。该方法能够精准有效地分割和识别磁瓦的表面缺陷，为磁瓦表面质量检测自动化行业提供了一种新的思路。

Abstract

In order to meet the high requirements of the magnetic tile production industry for surface quality inspection and realize the automatic segmentation and recognition of magnetic tile defects

a defect segmentation and classification network based on convolutional neural networks is proposed. The network is based on the U-net architecture. The deep features of defects are extracted through the U-net encoding part

and the deep features are used for defect classification

and then the segmented defect areas are output through the decoding part. In order to solve the problem that the proportion of the foreground area of some defects is too small

which makes the network difficult to converge

the continuous optimization of the network is ensured by adding the difference coefficient loss. Then

adding multiple layers of loss and performing online data enhancement in the training phase further improves the segmentation accuracy and classification accuracy. Experimental results show that with the addition of auxiliary loss function and data enhancement

the segmentation network can segment 94.5% of the marked defect areas

and the accuracy of defect classification can reach 98.9%

which meets the high precision requirements of the industry. This method can accurately and effectively segment and identify the surface defects of the magnetic tile

which provides a new idea for the automatic industry of magnetic tile surface quality inspection.

关键词

Keywords

references

X Q LI , H H JIANG , G F YIN . Detection of surface crack defects on ferrite magnetic tile . NDT & E International , 2014 . 62 6 - 13 . http://www.sciencedirect.com/science/article/pii/S0963869513001382 http://www.sciencedirect.com/science/article/pii/S0963869513001382 .

杨成立 , 殷国富 , 蒋红海 , 等 . 基于小波变换的磁瓦表面缺陷检测方法研究 . 计算机应用与软件 , 2014 . 31 ( 11 ): 210 - 213, 274 . https://www.cnki.com.cn/Article/CJFDTOTAL-JYRJ201411054.htm https://www.cnki.com.cn/Article/CJFDTOTAL-JYRJ201411054.htm .

C L YANG , G F YIN , H H JIANG , 等 . On magnetic tile surfaces defect detection based on wavelet transform . Computer Applications and Software , 2014 . 31 ( 11 ): 210 - 213, 274 . https://www.cnki.com.cn/Article/CJFDTOTAL-JYRJ201411054.htm https://www.cnki.com.cn/Article/CJFDTOTAL-JYRJ201411054.htm .

李雪琴 , 蒋红海 , 刘培勇 , 等 . 非下采样Contourlet域自适应阈值面的磁瓦表面缺陷检测 . 计算机辅助设计与图形学学报 , 2014 . 26 ( 4 ): 553 - 558 . https://www.cnki.com.cn/Article/CJFDTOTAL-JSJF201404006.htm https://www.cnki.com.cn/Article/CJFDTOTAL-JSJF201404006.htm .

X Q LI , H H JIANG , P Y LIU , 等 . Defect detection on magnetic tile surface based on adaptive threshold surfaces in NSCT domain . Journal of Computer-Aided Design & Computer Graphics , 2014 . 26 ( 4 ): 553 - 558 . https://www.cnki.com.cn/Article/CJFDTOTAL-JSJF201404006.htm https://www.cnki.com.cn/Article/CJFDTOTAL-JSJF201404006.htm .

林丽君 , 殷鹰 , 何明格 , 等 . 基于小波模极大值的磁瓦裂纹缺陷边缘检测算法 . 电子科技大学学报 , 2015 . 44 ( 2 ): 283 - 288 . https://www.cnki.com.cn/Article/CJFDTOTAL-DKDX201502024.htm https://www.cnki.com.cn/Article/CJFDTOTAL-DKDX201502024.htm .

L J LIN , Y YIN , M G HE , 等 . Edge detection algorithm of magnetic tile crack based on wavelet modulus maxima . Journal of University of Electronic Science and Technology of China , 2015 . 44 ( 2 ): 283 - 288 . https://www.cnki.com.cn/Article/CJFDTOTAL-DKDX201502024.htm https://www.cnki.com.cn/Article/CJFDTOTAL-DKDX201502024.htm .

T WANG , Y CHEN , M N QIAO , 等 . A fast and robust convolutional neural network-based defect detection model in product quality control . The International Journal of Advanced Manufacturing Technology , 2018 . 94 ( 9/12 ): 3465 - 3471 . http://link.springer.com/10.1007/s00170-017-0882-0 http://link.springer.com/10.1007/s00170-017-0882-0 .

S MEI , H YANG , Z P YIN . An unsupervised-learning-based approach for automated defect inspection on textured surfaces . IEEE Transactions on Instrumentation and Measurement , 2018 . 67 ( 6 ): 1266 - 1277 . DOI: 10.1109/TIM.2018.2795178 http://doi.org/10.1109/TIM.2018.2795178 .

王春哲 , 安军社 , 姜秀杰 , 等 . 基于卷积神经网络的候选区域优化算法 . 中国光学 , 2019 . 12 ( 6 ): 1348 - 1361 . https://www.cnki.com.cn/Article/CJFDTOTAL-ZGGA201906018.htm https://www.cnki.com.cn/Article/CJFDTOTAL-ZGGA201906018.htm .

C Z WANG , J S AN , X J JIANG , 等 . Region proposal optimization algorithm based on convolutional neural networks . Chinese Optics , 2019 . 12 ( 6 ): 1348 - 1361 . https://www.cnki.com.cn/Article/CJFDTOTAL-ZGGA201906018.htm https://www.cnki.com.cn/Article/CJFDTOTAL-ZGGA201906018.htm .

刘畅 , 张剑 , 林建平 . 基于神经网络的磁瓦表面缺陷检测识别 . 表面技术 , 2019 . 48 ( 8 ): 330 - 339 . https://www.cnki.com.cn/Article/CJFDTOTAL-BMJS201908044.htm https://www.cnki.com.cn/Article/CJFDTOTAL-BMJS201908044.htm .

C LIU , J ZHANG , J P LIN . Detection and identification of surface defects of magnetic tile based on neural network . Surface Technology , 2019 . 48 ( 8 ): 330 - 339 . https://www.cnki.com.cn/Article/CJFDTOTAL-BMJS201908044.htm https://www.cnki.com.cn/Article/CJFDTOTAL-BMJS201908044.htm .

RONNEBERGER O, FISCHER P, BROX T. U-Net: Convolutional networks for biomedical image segmentation[J]. arXiv : 1505.04597, 2015.

D TABERNIK , S ŠELA , J SKVAR , 等 . Segmentation-based deep-learning approach for surface-defect detection . Journal of Intelligent Manufacturing , 2020 . 31 ( 3 ): 759 - 776 . DOI: 10.1007/s10845-019-01476-x http://doi.org/10.1007/s10845-019-01476-x .

IOFFE S, SZEGEDY C. Batch normalization: accelerating deep network training by reducing internal covariate shift[J]. arXiv : 1502.03167, 2015.

MILLETARI F, NAVAB N, AHMADI S A. V-Net: fully convolutional neural networks for volumetric medical image segmentation[C]//2016 Fourth International Conference on 3 D Vision (3 DV ). Stanford, CA, USA: IEEE, 2016: 565-571.

ZENG G D, YANG X, LI J, et al . 3D U-net with multi-level deep supervision: fully automatic segmentation of proximal femur in 3D MR images[C]//8 th International Workshop on Machine Learning in Medical Imaging . Quebec City, QC, Canada: Springer, 2017: 274-282.

SIMONYAN K, ZISSERMAN A. Very deep convolutional networks for large-scale image recognition[J]. arXiv: 1409.1556, 2014.

HE K M, ZHANG X Y, REN S Q, et al . Deep residual learning for image recognition[J]. arXiv : 1512.03385, 2015.

CHOLLET F. Xception: deep learning with depthwise separable convolutions[J]. arXiv : 1610.02357, 2016.

SZEGEDY C, IOFFE S, VANHOUCKE V, et al . Inception-v4, Inception-ResNet and the impact of residual connections on learning[J]. arXiv : 1602.07261, 2016.

HUANG Y B, QIU C Y, GUO Y, et al . Surface defect saliency of magnetic tile[C]//2018 IEEE 14 th International Conference on Automation Science and Engineering ( CASE ). Munich, Germany: IEEE, 2018: 612-617.

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Design of heterogeneous FPGA hardware accelerator based on CNN

Lightweight image super-resolution combining residual learning and layer attention

Remote sensing image change detection based on CNN-Transformer structure

Wavefront correction method based on P-U-net for pyramid wavefront detector

Related Author

Jian XIE

Jian-min YAO

Qun YAN

Zhi-xian Lin

JI Haolin

XU Wei

PIAO Yongjie

WU Xiaobin

Related Institution

Jinjiang RichSense Electronic Technology Co.， Ltd.， Jinjiang

College of Physics and Information Engineering， Fuzhou University

Key Laboratory of Space-based Dynamic & Rapid Optical Imaging Technology， Chinese Academy of Sciences

University of Chinese Academy of Sciences

Changchun Institute of Optics， Fine Mechanics and Physics， Chinese Academy of Sciences

AI问答

Address：No.3888 Dong Nanhu Road, Changchun, Jilin, China 130033 Postal code：130033
Tel：0431-86176059 Email：yjxs@ciomp.ac.cn
Technical support is provided by Beijing Founder electronics co., LTD 吉ICP备11002662号-17 京公网安备11010802024621
It is recommended to read the content of this site in Chrome&IE9+. Please switch to extreme mode in browser 360.
Cookies We use cookies to help provide and enhance our service and tailor content. By continuing, you agree to the use of cookies.

⁰