计算机科学

计算机科学 ›› 2023, Vol. 50 ›› Issue (6A): 220300224-6.doi: 10.11896/jsjkx.220300224

• 图像处理&多媒体技术 • 上一篇    下一篇

基于改进Cascade R-CNN的布匹瑕疵检测算法

白明丽, 王明文   

  1. 西南交通大学数学学院 成都 611756
  • 出版日期:2023-06-10 发布日期:2023-06-12
  • 通讯作者: 王明文(wangmw@swjtu.edu.cn)
  • 作者简介:(Baiml@my.swjtu.edu.cn)
  • 基金资助:
    中央高校基本科研业务费专项资金(2682021ZTPY100);四川省科技计划项目(2020YFG0238)

Fabric Defect Detection Algorithm Based on Improved Cascade R-CNN

BAI Mingli, WANG Mingwen   

  1. School of Mathematics,Southwest Jiaotong University,Chengdu 611756,China
  • Online:2023-06-10 Published:2023-06-12
  • About author:BAI Mingli,born in 1997,master student.Her main research interests include artificial intelligence,computer vision and machine learning. WANG Mingwen,born in 1973,Ph.D,associate professor,is a member of China Computer Federation.His main research interests include information security and artificial intelligence.
  • Supported by:
    Fundamental Research Funds for the Central Universities(2682021ZTPY100) and Science and Technology Plan Project of Sichuan Province(2020YFG0238).

PDF (PC)

280

摘要： 布匹瑕疵的自动化检测是目前纺织行业面临的一个难点问题。针对当前布匹瑕疵检测算法对尺度和长宽比变化大、小目标众多的样本检测效果并不理想的问题,提出了基于改进Cascade R-CNN网络的布匹瑕疵检测算法。首先,在特征提取网络ResNet-50中融入可变形卷积,自适应地提取更多的瑕疵形状与尺度特征;其次,在特征金字塔网络上采样前引入平衡特征金字塔,缩小特征融合前各特征层之间的语义差距,得到更具表达力的多尺度特征;然后,根据瑕疵尺度与长宽比特点重新设计更适合的初始锚框;最后,采用具有尺度不变性的GIoU Loss作为级联检测器的回归损失,以获取更加精确的瑕疵预测边界框。实验结果表明,相比基于Cascade R-CNN的算法,改进后的Cascade R-CNN算法对布匹瑕疵检测的平均精确率获得了明显提升。

关键词: Cascade R-CNN, 布匹瑕疵检测, 可变形卷积, 平衡特征金字塔, GIoU Loss

Abstract: Automatic detection of fabric defects is a difficult problem in textile industry.To solve the problem that the current fabric defect detection algorithms have unsatisfactory detection effect on samples with large scale and aspect ratio changes and numerous small targets,a fabric defect detection algorithm based on improved Cascade R-CNN network is proposed.The main improvements are as follows.Firstly,deformable convolution is incorporated into the feature extraction network ResNet-50 to extract more shape and scale features of defects adaptively.Secondly,balanced feature pyramid is introduced in the feature pyramid network before sampling to narrow the semantic gap between each feature layer before feature fusion and get more expressive multi-scale features.Then,more suitable initial anchor boxes are redesigned according to the scale and aspect ratio of defects.Finally,GIoU Loss with scale invariance is used as the regression loss of cascade detector to obtain more accurate defect prediction boundary boxes.Experimental results show that compared with the algorithm based on Cascade R-CNN,the improved Cascade R-CNN algorithm significantly improves the average precision of fabric defect detection.

Key words: Cascade R-CNN, Fabric defect detection, Deformable convolution, Balanced feature pyramid, GIoU Loss

中图分类号: 

  • TP391
[1]AJAY K.Computer vision based fabric defect detection:A survey.IEEE Transactions on Industrial Electronics,2008,55(1):348-363.
[2]GUAN M.Study on Fabric Defect Detection Methods Based on Intelligent Learning Algorithm[D].Suzhou:Soochow University,2019.
[3]HU G H,WANG Q H,ZHANG G H.Unsupervised defect detection in textiles based on Fourier analysis and wavelet shrin-kage[J].Applied Optics,2015,54(10):2963-2980.
[4]TONG L,WONG W K,KWONG C K.Differential evolution-based optimal Gabor filter model for fabric inspection[J].Neurocomputing,2016,173:1386-1401.
[5]LI P,ZHANG H,JING J,et al.Fabric defect detection based on multi-scale wavelet transform and Gaussian mixture model method[J].The Journal of The Textile Institute,2015,106(6):587-592.
[6]JI H J,ZHANG X D,YANG J M.Discussion on the Detection Technology of Fabric Defects Based on Machine Vision[J].Advanced Textile Technology,2011,19(2):11-15.
[7]RAHEJA J L,AJAY B,CHAUDHARY A.Real time fabric defect detection system on an embedded DSP platform[J].Optik,2013,124(21):5280-5284.
[8]HU J,HE Z,WENG G,et al.Detection of chemical fabric defects on the basis of morphological processing[J].The Journal of The Textile Institute,2016,107(2):233-241.
[9]ZHONG Z Z,QI P J,GUAN M,et al.Fabric defect detection system based on digital image processing[J].Computer Modelling and New Technologies,2014,18(10):263-270.
[10]HANMANDLU M,CHOUDHURY D,Dash S.Detection of defects in fabrics using topothesy fractal dimension features[J].Signal,Image and Video Processing,2015,9(7):1521-1530.
[11]REN S,HE K,GIRSHICK R,SUN J.Faster R-CNN:Towards real-time object detection with region proposal networks[C]//Proceedings of the Neural Information Processing Systems.2015:91-99.
[12]LIU W,ANGUELOV D,ERHAN D,et al.SSD:Single shot multibox detector[C]//Proceedings of the European Conference on Computer Vision.2016:21-37.
[13]REDMON J,DIVVALA S,GIRSHICK R,et al.You only look once:Unified,real-time object detection[C]//Proceedings of the Computer Vision and Pattern Recognition.2016:779-788.
[14]REDMON J,FARHADI A.YOLO9000:Better,faster,stronger[C]//Proceedings of the Computer Vision and Pattern Recognition.2017:7263-7271.
[15]REDMON J,FARHADI A.Yolov3:An incremental improve-ment[J].arXiv:1804.02767,2018.
[16]JING J F,FANG X T,LI P F,et al.Yarn-dyed Fabric Defect Detection Based on Deep Convolutional Neural Network[J].Journal of Textile Research,2017,38(2):68-74.
[17]LIU Z,LIU X,LI C,et al.Fabric Defect Detection Based on Faster R-CNN[C]//International Conference on Graphic and Image Processing.2018:106-115.
[18]GIRSHICK R.Fast R-CNN[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.Pisca-taway,USA:IEEE,2015:1440-1448.
[19]XU Y G,ZHONG M,WU Z Z,et al.Detection of Detecting Textured Fabric Defects Based on Deep Learning[J].Acta Automatica Sinica,2023,49(4):857-871.
[20]CAI Z W,VASCONCELOS N.Cascade R-CNN:Delving intoHigh Quality Object Detection[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.Washington,USA:IEEE,2018:6154-6162.
[21]DAI J,QI H,XIONG Y,et al.Deformable Convolutional Networks[C]//IEEE Conference on Computer Vision and Pattern Recognition.2017:764-773.
[22]HE K,ZHANG X,REN S,et al.Deep residual learning forimage recognition[C]//Proceedings of the Computer Vision and Pattern Recognition.2016:770-778.
[23]LIN T Y,DOLLAR P,GIRSHICK R,et al.Feature pyramidnetworks for object detection[C]//Proceedings of the Compu-ter Vision and Pattern Recognition.2017:2117-2125.
[24]PANG J,CHEN K,SHI J,et al.Libra R-CNN:Towards balanced learning for object detection[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.2019:821-830.
[25]HAMID R,NATHAN T,JUN Y G,et al.Generalized intersection over union:A metric and a loss for bounding box regression[C]//CVF Conference on Computer Vision and Pattern Recognition.Long Beach,CA,USA.IEEE,2019:658-666.
[26]YU J H,JIANG Y,WANG Z,et al.UnitBox:An advanced object detection network[C]//Proceedings of the 24th ACM international conference on Multimedia.Amsterdam The Netherlands.New York,NY,USA:ACM,2016:516-520.
[27]TIANCHI.Smart Diagnosis of Cloth FlawDatas-et/布匹瑕疵检测数据集[EB/OL].(2020-10-21)[2022-03-21].https://tianchi.aliyun.com/dataset/dataDetail?dataId=79336.
[28]ZHANG S,CHI C,YAO Y,et al.Bridging the gap between anchor-based and anchor-free detection via adaptive training sample selection[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition CVPR.Seattle,WA,USA,2020:13-19.
[29]SUN P Z,ZHANG R F, JIANG Y,et al.Sparse R-CNN:End-to-End Object Detection with Learnable Proposals[C]//Procee-dings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition CVPR.Elect Network,2021:19-25.
Viewed
Full text


Abstract

Cited
  Shared   
  Discussed   
No Suggested Reading articles found!
渝ICP备16013121号-4
地址：重庆市渝北区洪湖西路18号    邮编：401121  
电话：023-63500828（编辑部） 023-67039612（会议/专题） 023-67039623（财务/发票）
E-mail：jsjkx12@163.com
本系统由北京玛格泰克科技发展有限公司设计开发