Research on Ceramic Tile Surface Defect Detection by Improved Faster RCNN

doi:10.3778/j.issn.1002-8331.2203-0414

Abstract

Abstract: Aiming at the problems of minimal defect target, large difference of defect shape, easy missing detection and low accuracy in ceramic tile surface defects, an improved ceramic tile surface defect detection algorithm based on Faster RCNN is proposed. Firstly, based on the original Faster RCNN, resnet101 is selected as the feature extraction network, and deformable convolution networks is introduced in the last three stages of resnet101 to adaptively learn the defect features. Secondly, the regional proposals network is optimized, and the anchor generation parameters are improved through the analysis of ceramic tile data set, so that the generated anchors are more consistent with the target scale and the positioning is more accurate. Finally, the loss function is optimized and Rank & Sort Loss is introduced to reduce the number of super parameters and improve the performance of the model, making it more robust to the class imbalance problem in training. Experimental results show that the average detection accuracy of the improved Faster RCNN is 76.3%, which is 17.9 percentage points higher than that of Faster RCNN. It can better detect small target defects and meet the requirements of ceramic tile surface defect detection.

Key words: target detection, ceramic tile surface defect, Faster RCNN, Rank &, Sort Loss, deformable convolution networks

摘要： 针对瓷砖表面瑕疵中存在极小瑕疵目标，瑕疵形态差异较大，易出现漏检、准确率低等问题，提出了一种改进Faster RCNN的瓷砖表面瑕疵检测算法。在Faster RCNN的特征提取网络resnet101的后三个阶段引入可变形卷积，自适应地学习瑕疵特征。优化区域建议网络，通过对瓷砖数据集的分析，改进锚点生成参数，使得生成的锚框更加契合目标尺度，定位更加准确。优化损失函数，引入Rank & Sort Loss，减少超参数数量，提高模型性能，使其对训练中类别不平衡问题更加鲁棒。实验结果表明，改进后算法的mAP为76.3%，比原始Faster RCNN算法提高了17.9个百分点，可以更好地检测小目标瑕疵，满足瓷砖表面瑕疵检测的要求。

关键词: 目标检测, 瓷砖表面瑕疵, Faster RCNN, Rank &, Sort Loss, 可变形卷积

ZHAO Chu, DUAN Xianhua, SU Junkai. Research on Ceramic Tile Surface Defect Detection by Improved Faster RCNN[J]. Computer Engineering and Applications, 2023, 59(14): 201-208.

赵楚, 段先华, 苏俊楷. 改进Faster RCNN的瓷砖表面瑕疵检测研究[J]. 计算机工程与应用, 2023, 59(14): 201-208.

References

[1] 李治.陶瓷砖质量发展概述[C]//第四届建筑卫生陶瓷质量大会暨中国硅酸盐学会建筑卫生陶瓷专业委员会2019学术年会论文集，2019：15-16.
LI Z.Overview of ceramic tile quality development[C]//Proceedings of the 4th Architectural and Sanitary Ceramics Quality Conference and 2019 Professional Committee of China Silicate Society Academic Annual Meeting of Architectural and Sanitary Ceramics，2019：15-16.
[2] 肖克来提.表面缺陷检测应用研究综述[J].电子技术，2020，49（8）：189-191.
SHOCKLETTI.Review on application of surface defect detection[J].Electronic Technology，2020，49（8）：189-191.
[3] 杨传礼，张修庆.基于机器视觉和深度学习的材料缺陷检测应用综述[J].材料导报，2022（16）：1-19.
YANG C L，ZHANG X Q.Survey of material defect detection applications based on machine vision and deep learning[J].Materials Reports，2022（16）：1-19.
[4] 李光亚，邹国锋，傅桂霞.基于Gabor变换与区域生长的瓷砖表面缺陷视觉检测方法研究[J].现代计算机，2019（24）：37-42.
LI G Y，ZOU G F，FU G X.Research on visual inspection method of ceramic tile surface defects based on Gabor transform and region growth[J].Modern Computer，2019（24）：37-42.
[5] 李军华，权小霞，汪宇玲.多特征融合的瓷砖表面缺陷检测算法研究[J].计算机工程与应用，2020，56（15）：191-198.
LI J H，QUAN X X，WANG Y L.Research on defect detection algorithm of ceramic tile surface with multi-feature fusion[J].Computer Engineering and Applications，2020，56（15）：191-198.
[6] LIU W，ANGUELOV D，ERHAN D.SSD：single shot multibox detector[C]//European Conference on Computer Vision.Cham：Springer，2016：21-37.
[7] REDMON J，DIVVALA S，GIRSHICK R，et al.You only look once：unified，real-time object detection[C]//Computer Vision & Pattern Recognition，2016：779-788.
[8] REDMON J，FARHADI A.YOLO9000：better，faster，stronger[C]//IEEE Conference on Computer Vision & Pattern Recognition，2017：6517-6525.
[9] REDMON J，FARHADI A.YOLOv3：an incremental improvement[C]//IEEE Conference on Computer Vision & Pattern Recognition，2018：2767-2773.
[10] BOCHKOVSKIY A，WANG C Y，LIAO H Y M.YOLOv4：optimal speed and accuracy of object detection[C]//IEEE Conference on Computer Vision and Pattern Recognition，2020.
[11] GIRSHICK R.Fast R-CNN[C]//Proceedins of the IEEE Conference on Computer Vision and Pattern Recognition，2015：1440-1448.
[12] REN S，HE K，GIRSHICK R.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.
[13] HE K，GKIOXARI G，PIOTR D，et al.Mask RCNN[J].IEEE Transactions on Pattern Analysis & Machine Intelligence，2017：2961-2969.
[14] 陈学仕，苏通，漆为民.基于改进Faster RCNN的印刷电路板瑕疵检测算法[J].江汉大学学报（自然科学版），2022，50（1）：87-96.
CHEN X S，SU T，QI W M.Printed circuit board defect detection algorithm based on improved faster RCNN[J].Journal of Jianghan University（Natural Science Edition），2022，50（1）：87-96.
[15] 程婧怡，段先华，朱伟.改进YOLOv3的金属表面缺陷检测研究[J].计算机工程与应用，2021，57（19）：252-258.
CHENG J Y，DUAN X H，ZHU W.Research on metal surface defect detection by improved YOLOv3[J].Computer Engineering and Applications，2021，57（19）：252-258.
[16] 安萌，郑飂默，王诗宇.一种改进Faster R-CNN的面料疵点检测方法[J].小型微型计算机系统，2021，42（5）：1029-1033.
AN M，ZHENG L M，WANG S Y.Fabric defect detection method based on improved faster R-CNN[J].Journal of Chinese Computer Systems，2021，42（5）：1029-1033.
[17] OKSUZ K，CAM B C，AKBAS E，et al.Rank & sort loss for object detection and instance segmentation[C]//2021 IEEE/CVF International Conference on Computer Vision（ICCV），2021：2989-2998.
[18] HE K，ZHANG X，REN S.Deep residul learning for image recognition[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition（CVPR），2016：770-778.
[19] LIN T，DOLLAR P，GIRSHICK R，et al.Feature pyramid networks for object detection[C]//IEEE Conference on Computer Vision and Pattern Recognition（CVPR），2017：936-944.
[20] DAI J F，QI H Z，XIONG Y W，et al.Deformable convolutional networks[C]//Proceedings of 2017 IEEE International Conference on Computer Vision，2017：764-773.
[21] CAI Z，VASCONCELOS N.Cascade R-CNN：delving into high quality object detection[C]//Computer Vision and Pattern Recognition，2018：6154-6162.