Magnetic tile surface quality recognition based on multi-scale convolution neural network and within-class mixup operation

doi:10.11772/j.issn.1001-9081.2020060886

Journal of Computer Applications ›› 2021, Vol. 41 ›› Issue (1): 275-279.DOI: 10.11772/j.issn.1001-9081.2020060886

Special Issue: 第八届中国数据挖掘会议(CCDM 2020)

• China Conference on Data Mining 2020 (CCDM 2020) • Previous Articles Next Articles

Magnetic tile surface quality recognition based on multi-scale convolution neural network and within-class mixup operation

ZHANG Jing'ai¹, WANG Jiangtao^1,2

1. School of Physics and Electronic Information, Huaibei Normal University, Huaibei Anhui 235000, China;
2. School of Information, Huaibei Normal University, Huaibei Anhui 235000, China

Received:2020-05-30 Revised:2020-07-13 Online:2021-01-10 Published:2020-11-12
Supported by:
This work is partially supported by the Natural Science Research Project for Colleges in Anhui Province (KJ2018ZD038, KJ2019B15), the Anhui Provincial Quality Engineering Project (2019jxtd142).

基于多尺度卷积神经网络和类内mixup操作的磁瓦表面质量识别

张京爱¹, 王江涛^1,2

1. 淮北师范大学物理与电子信息学院, 安徽淮北 235000;
2. 淮北师范大学信息学院, 安徽淮北 235000

通讯作者: 王江涛
作者简介:张京爱(1980-),女,山东潍坊人,实验师,硕士,主要研究方向:数字图像处理、缺陷检测;王江涛(1979-),男,山东昌乐人,教授,博士,CCF会员,主要研究方向:模式识别、深度学习、目标检测。
基金资助:
安徽省高校自然科学研究项目（KJ2018ZD038，KJ2019B15）；安徽省质量工程项目（2019jxtd142）。

Abstract

Abstract: The various shapes of ferrite magnetic tiles and the wide varieties of their surface defects are great challenges for computer vision based surface defect quality recognition. To address this problem, the deep learning technique was introduced to the magnetic tile surface quality recognition, and a surface defect detection system for magnetic tiles was proposed based on convolution neural networks. Firstly, the tile target was segmented from the collected image and was rotated in order to obtain the standard image. After that, the improved multiscale ResNet18 was used as the backbone network to design the recognition system. During the training process, a novel within-class mixup operation was designed to improve the generalization ability of the system on the samples. To close to the practical application scenes, a surface defect dataset was built with the consideration of illumination changes and posture differences. Experimental results on the self-built dataset indicate that the proposed system achieves recognition accuracy of 97.9%, and provides a feasible idea for the automatic recognition of magnetic tile surface defects.

Key words: magnetic tile, surface defect detection, convolution neural network, mixup, ResNet18

摘要： 铁氧体磁瓦由于形状的不规则性和表面缺陷的多样性给基于计算机视觉的表面质量识别带来很大的挑战。针对该问题，将深度学习技术引入到磁瓦表面质量识别中，提出一种基于卷积神经网络的磁瓦表面质量识别系统。首先将磁瓦目标从采集到的图像中分割出来并进行旋转从而得到标准图像，然后把改进后的多尺度ResNet18作为骨干网络来设计识别系统。训练时，设计一种新颖的类内mixup操作来提高系统对样本的泛化能力。为了更加贴近实际应用场景，在考虑到光线变化、姿态差异等因素的前提下构建了磁瓦缺陷数据集。在自建的数据集中进行实验的结果表明，该系统可以达到97.9%的识别准确率，为磁瓦缺陷的自动识别提供了可行的思路。

关键词: 磁瓦, 表面缺陷检测, 卷积神经网络, mixup, ResNet18

CLC Number:

TP391

ZHANG Jing'ai, WANG Jiangtao. Magnetic tile surface quality recognition based on multi-scale convolution neural network and within-class mixup operation[J]. Journal of Computer Applications, 2021, 41(1): 275-279.

张京爱, 王江涛. 基于多尺度卷积神经网络和类内mixup操作的磁瓦表面质量识别[J]. 计算机应用, 2021, 41(1): 275-279.

References

[1] TABERNIK D,ŠELA S,SKVARČ J,et al. Segmentation-based deep-learning approach for surface-defect detection[J]. Journal of Intelligent Manufacturing,2019,31(3):759-776.
[2] TRUONG M T N,KIM S. Automatic image thresholding using Otsu's method and entropy weighting scheme for surface defect detection[J]. Soft Computing,2018,22(13):4197-4203.
[3] FEKRI-ERSHAD S,TAJERIPOUR F. Multi-resolution and noiseresistant surface defect detection approach using new version of local binary patterns[J]. Applied Artificial Intelligence,2017,31(5/6):395-410.
[4] BULNES F G,USAMENTIAGA R,GARCIA D F,et al. An efficient method for defect detection during the manufacturing of web materials[J]. Journal of Intelligent Manufacturing,2016,27(2):431-445.
[5] 胡浩, 李俊峰, 沈军民. 基于机器视觉的小磁瓦表面微缺陷检测方法研究[J]. 机电工程,2019,36(2):117-123,184.(HU H,LI J F,SHEN J M. Detection methods for surface micro defection on small magnetic tile based on machine vision[J]. Journal of Mechanical and Electrical Engineering, 2019, 36(2):117-123,184.)
[6] 刘国平, 常震, 胡瑢华. 磁瓦表面图像的下包络线灰度对比度缺陷检测算法[J]. 机械科学与技术,2017,36(2):269-272.(LIU G P,CHANG Z,HU R H. Defect extraction on magnetic tile surfaces based on lower envelope gray-scale contrast[J]. Mechanical Science and Technology for Aerospace Engineering, 2017,36(2):269-272.)
[7] 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[J]. 计算机辅助设计与图形学学报, 2014,26(4):553-558.(LI X Q,JIANG H H,LIU P Y,et al. Defect detection on magnetic tile surface based on adaptive threshold surfaces in NSCT domain[J]. Journal of Computer-Aided Design and Computer Graphics,2014,26(4):553-558.)
[8] 林丽君, 殷鹰, 李雪琴, 等. 基于轮廓波包变换的磁瓦表面缺陷提取[J]. 应用基础与工程科学学报,2016,24(2):402-417. (LIN L J,YIN Y,LI X Q,et al. Defect extraction on magnetic tile surface based on contourlet packet transform[J]. Journal of Basics Science and Engineering,2016,24(2):402-417.)
[9] REN S,HE K,GIRSHICK R,et al. Faster R-CNN:towards realtime object detection with region proposal networks[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,2017, 39(6):1137-1149.
[10] LIN T Y,GOYAL P,GIRSHICK R,et al. Focal loss for dense object detection[C]//Proceedings of 2017 IEEE International Conference on Computer Vision. Piscataway:IEEE,2017:2999-3007.
[11] SIMONYAN K, ZISSERMAN A. Very deep convolutional networks for large-scale image recognition[EB/OL].[2020-03-14]. https://arxiv.org/pdf/1409.1556.pdf.
[12] HE K,ZHANG X,REN S,et al. Deep residual learning for image recognition[C]//Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway:IEEE, 2016:770-778.
[13] ZHANG H,CISSE M,DAUPHIN Y N,et al. mixup:Beyond empirical risk minimization[EB/OL].[2020-03-14]. https://arxiv.org/pdf/1710.09412.pdf.
[14] 康鑫, 孙晓刚, 万磊. 复杂场景下的水表示数检测与识别[J]. 计算机应用,2019,39(S2):63-67.(KANG X,SUN X G,WAN L. Watermeter representation number detection and recognition in complex scenes[J]. Journal of Computer Applications,2019,39(S2):63-67.)
[15] 邓棋, 雷印杰, 田锋. 用于肺炎图像分类的优化卷积神经网络方法[J]. 计算机应用,2020,40(1):71-76.(DENG Q,LEI Y J,TIAN F. Optimized convolutional neural network method for classification of pneumonia images[J]. Journal of Computer Applications,2020,40(1):71-76.)

Magnetic tile surface quality recognition based on multi-scale convolution neural network and within-class mixup operation

基于多尺度卷积神经网络和类内mixup操作的磁瓦表面质量识别

PDF

Knowledge

Abstract

Cite this article

share this article

References

Related Articles 15

Recommended Articles

Metrics

[1]	NIU Kangli, CHEN Yuzhang, SHEN Junfeng, ZENG Zhangfan, PAN Yongcai, WANG Yichong. Dual-channel night vision image restoration method based on deep learning [J]. Journal of Computer Applications, 2021, 41(6): 1775-1784.
[2]	SHI Yangxiao, ZHANG Jun, CHEN Peng, WANG Bing. Classification of steel surface defects based on lightweight network [J]. Journal of Computer Applications, 2021, 41(6): 1836-1841.
[3]	FU Ying, WANG Hongling, WANG Zhongqing. Scientific paper summarization model using macro discourse structure [J]. Journal of Computer Applications, 2021, 41(10): 2864-2870.
[4]	YIN Chunyong, HE Miao. Text classification based on improved capsule network [J]. Journal of Computer Applications, 2020, 40(9): 2525-2530.
[5]	YE Yang, CAI Qiong, DU Xiaobiao. Single image super-resolution method based on non-local channel attention mechanism [J]. Journal of Computer Applications, 2020, 40(12): 3618-3623.
[6]	DENG Tianmin, FANG Fang, ZHOU Zhenhao. Traffic sign recognition based on improved convolutional neural network with spatial pyramid pooling [J]. Journal of Computer Applications, 2020, 40(10): 2872-2880.
[7]	DU Nianmao, XU Jiachen, XIAO Zhiyong. Undersampled brain magnetic resonance image reconstruction method based on convolutional neural network [J]. Journal of Computer Applications, 2020, 40(10): 3060-3065.
[8]	CHENG Junhua, ZENG Guohui, LU Dunke, HUANG Bo. Improved convolution neural network model averaging method based on Dropout [J]. Journal of Computer Applications, 2019, 39(6): 1601-1606.
[9]	JI Shuwei, YANG Xiwang, HUANG Jinying, YIN Ning. Model compression method of convolution neural network based on feature-reuse [J]. Journal of Computer Applications, 2019, 39(6): 1607-1613.
[10]	HE Xinyu, ZHANG Xiaolong. Pneumonia image recognition model based on deep neural network [J]. Journal of Computer Applications, 2019, 39(6): 1680-1684.
[11]	CAI Ruichu, ZHONG Chunrong, YU Yang, CHEN Bingfeng, LU Ye, CHEN Yao. CNN quantization and compression strategy for edge computing applications [J]. Journal of Computer Applications, 2018, 38(9): 2449-2454.
[12]	YANG Chunni, FENG Chaosheng. Multi-intention recognition model with combination of syntactic feature and convolution neural network [J]. Journal of Computer Applications, 2018, 38(7): 1839-1845.
[13]	TAN Jiefan, ZHU Yan, CHEN Tung-shou, CHANG Chin-chen. Imbalanced image classification approach based on convolution neural network and cost-sensitivity [J]. Journal of Computer Applications, 2018, 38(7): 1862-1865.
[14]	WEI Zhenyu, WEN Chang, XIE Kai, HE Jianbiao. Real-time face detection for mobile devices with optical flow estimation [J]. Journal of Computer Applications, 2018, 38(4): 1146-1150.
[15]	HU Xuemin, YI Chonghui, CHEN Qin, CHEN Xi, CHEN Long. Abnormal crowd behavior detection based on motion saliency map [J]. Journal of Computer Applications, 2018, 38(4): 1164-1169.