Strip Surface Defect Detection Based on Improved Mask R-CNN Algorithm

doi:10.3778/j.issn.1002-8331.2010-0446

Abstract

Abstract:

In the production process of strip steel, the surface defects of strip steel may be caused by the problems of production process. The traditional surface detection methods of strip steel have the problems of slow detection speed and low detection accuracy. With the rapid development of computer deep learning, in order to achieve rapid and effective detection of strip surface defect, this paper proposes a new algorithm based on improved Mask Region Convolution Neural Network（Mask R-CNN）, and uses [k]-means II clustering algorithm to improve the anchor frame generation method of Region Proposal Network（RPN）. At the same time, it adjusts the network structure of Mask R-CNN, removes the mask branches, and improves the defect detection speed of the model. In the experiments, the mean Average Precision（mAP） of the original algorithm is improved from 0.810?2 to 0.960?2 in 5 kinds of defect detections of NEU-DET data set, and the detection speed reaches 5.9?frame/s. And it can detect the defect target and segment the case, so that researchers can observe the size and shape of the defect, so as to improve the process. Compared with other deep learning defect detection algorithms, it can better meet the requirements of strip production detection.

Key words: deep learning, strip surface defect detection, anchor box, clustering algorithm, mask branching

摘要：

在带钢的生产过程中可能会因为生产工艺的问题导致带钢表面出现缺陷，传统的带钢表面检测方法存在检测速度慢、检测精度低等问题。在计算机深度学习快速发展的今天，为实现带钢表面缺陷快速有效的检测，提出改进的掩码区域卷积神经网络（Mask R-CNN）算法，使用[k]-means II聚类算法改进区域建议网络（RPN）锚框生成方法；同时调整Mask R-CNN模型的网络结构，去掉掩码分支，提高了模型的缺陷检测速度。实验在NEU-DET数据集的5种缺陷检测中将原算法的均值平均精度（mAP）从0.810?2提升到0.960?2，检测速度达到5.9?frame/s。并且能够实现对缺陷目标的检测和实例分割，以便研究人员观测缺陷的大小和形状，从而改进工艺。相比于目前其他深度学习的缺陷检测算法，更能满足带钢的生产检测要求。

关键词: 深度学习, 带钢表面缺陷检测, 锚框, 聚类算法, 掩码分支

WENG Yushang, XIAO Jinqiu, XIA Yu. Strip Surface Defect Detection Based on Improved Mask R-CNN Algorithm[J]. Computer Engineering and Applications, 2021, 57(19): 235-242.

翁玉尚，肖金球，夏禹. 改进Mask R-CNN算法的带钢表面缺陷检测[J]. 计算机工程与应用, 2021, 57(19): 235-242.

References

[1] GIRSHICK R，DONAHUE J，DARRELL T，et al.Rich feature hierarchies for accurate object detection and semantic segmentation[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.Los Alamitos：IEEE Computer Society Press，2014：580-587.
[2] GIRSHICK R.Fast R-CNN[C]//Proceedings of the IEEE International Conference on Computer Vision.Los Alamitos：IEEE Computer Society Press，2015：1440-1448.
[3] REN S Q，HE K M，GIRSHICK R，et al.Faster R-CNN：Towards real-time object detection with region proposal networks[J].IEEE Transactions on Pattern Analysis and Machine Intelligence，2017，39（6）：1137-1149.
[4] HE K M，GKIOXARI G，DOLLáR P，et al.Mask R-CNN[C]//Proceedings of the IEEE International Conference on Computer Vision.Los Alamitos：IEEE Computer Society Press，2017：2961-2969.
[5] SERMANET P，EIGEN D，ZHANG X，et al.OverFeat：Integrated recognition，localization and detection using convolutional neworks[EB/OL].[2020-09-15].https：//arxiv.org/abs/1312.6229.
[6] REDMON J，DIVVALA S，GIRSHICK R，et al.You only look once：unified，real-time object detection[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.Los Alamitos：IEEE Computer Society Press，2016：779-788.
[7] REDMON J，FARHADI A.YOLO9000：Better，faster，stronger[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.Los Alamitos：IEEE Computer Society Press，2017：7263-7271.
[8] REDMON J，FARHADI A.YOLOv3：An incremental improvement[EB/OL].[2019-09-15].https：//arxiv.org/abs/1804.02767.
[9] LIU W，ANGUELOV D，ERHAN D，et al.SSD：single shot multiBox detector[C]//Proceedings of European Conference on Computer Vision.Heidelberg：Springer，2016：21-37.
[10] 陶显圣，侯伟，徐德.基于深度学习的表面缺陷检测方法综述[J].自动化学报，2021，47（5）：1017-1034.
TAO X S，HOU W，HE W F.Survey of surface defect detection methods based on deep learning[J].Acta Automatica Sinica，2021，47（5）：1017-1034.
[11] CHA Y J，CHOI W，SUH G，et al.Autonomous structural visual inspection using region based deep learning for detecting multiple damage types[J].Computer-Aided Civil and Infrastructure Engineering，2018，33（9）：731-747.
[12] 马晓云，朱丹，金晨，等.基于改进的Faster R-CNN的子弹外观缺陷检测[J].激光与光电子进展，2019，56（15）：117-124.
MA X Y，ZHU D，JIN C H，et al.Bullet appearance defect detection based on improved faster rgion-convolutional neural network[J].Laser & Optoelectronics Progress，2019，56（15）：117-124.
[13] 裴伟，许宴铭，朱永英，等.改进的SSD航拍目标检测方法[J].软件学报，2019，30（3）：738-758.
PEI W，XU Y M，ZHU Y Y，et al.The target detection metho-d of aerial photography images with improved SSD[J].Journal of Software，2019，30（3）：738-758.
[14] 王俊强，李建盛，周学文，等.改进的SSD算法对遥感影像小目标检测性能的分析[J].光学学报，2019，39（6）：373-382.
WANG J Q，LI J S，ZHOU X W，et al.Improved SSD algorithm and its performance analysis of small target detection in remote sensing images[J].Acta Optica Sinica，2019，39（6）：373-382.
[15] FU G Z，SUN P Z，ZHU W B，et al.A deep-learning-based approach for fast and robust steel surface defects classification[J].Optics and Lasers in Engineering，2019，121（10）：397-405.
[16] HE Y，SONG K C，MENG Q G，et al.Semi-supervised defect classification of steel surface based on multi-training and generative adversarial network[J].Optics and Lasers in Engineering，2019，122（11）：294-302.
[17] HE Y，SONG K，MENG Q，et al.An end-to-end steel surface defect detection approach via fusing multiple hierarchical features[J].IEEE Transactions on Instrumentation and Measurement，2020，69（4）：1493-1504.
[18] SHELHAMER E，LONG J，DAARREL T.Fully convolutional networks for semantic[J].IEEE Transactions on Pattern Analysis and Machine Intelligence，2017，39（4）：640-651.
[19] 杨俊闯，赵超.K-Means聚类算法研究综述[J].计算机工程与应用，2019，55（23）：7-14.
YANG J C，ZHAO C.Survey on K-means clustering algorithm[J].Computer Engineering and Applications，2019，55（23）：7-14.