<-上一篇/Previous Article 下一篇/Next Article->

[1]王延春秋,葛泉波,刘华平.石板材表面缺陷检测的无监督学习方法[J].智能系统学报,2023,18(6):1344-1351.[doi:10.11992/tis.202212006]
　WANG Yanchunqiu,GE Quanbo,LIU Huaping.Unsupervised learning method for surface defect detection of slate materials[J].CAAI Transactions on Intelligent Systems,2023,18(6):1344-1351.[doi:10.11992/tis.202212006]

点击复制

石板材表面缺陷检测的无监督学习方法

PDF下载 HTML

《智能系统学报》[ISSN 1673-4785/CN 23-1538/TP] 卷: 18 期数: 2023年第6期页码: 1344-1351 栏目: 吴文俊人工智能科学技术奖论坛出版日期: 2023-11-05

Title:: Unsupervised learning method for surface defect detection of slate materials

作者:: 王延春秋¹, 葛泉波², 刘华平³; 1. 上海海事大学物流工程学院, 上海 201306;
2. 南京信息工程大学自动化学院, 江苏南京 210044;
3. 清华大学计算机科学与技术系, 北京 100084

Author(s):: WANG Yanchunqiu¹, GE Quanbo², LIU Huaping³; 1. Logistics Engineering College, Shanghai Maritime University, Shanghai 201306, China;
2. School of Automation, Nanjing University of Information Science & Technology, Nanjing 210044, China;
3. Department of Computer Science and Technology, Tsinghua University, Beijing 100084, China

关键词:: 石板材; 表面缺陷; 缺陷检测; 无监督学习; 多尺度特征; 半正交嵌入特征; 特征学习; 马氏距离

Keywords:: slate; surface defects; defect detection; unsupervised learning; multiscale feature; semiorthogonal embedding feature; feature learning; mahalanobis distance

分类号:: TP391

DOI:: 10.11992/tis.202212006

摘要:: 石板材表面缺陷检测是一项具有挑战性的任务，尤其对于边缘磕碰、裂缝等细微缺陷，检测难度大。此外，冗余特征的存在会影响训练效果，多尺度特征学习需要进行多维计算，计算复杂度高。针对上述问题，本文提出一种基于无监督学习的石板材表面缺陷检测方法，它能够有效解决该任务存在的问题。首先，对预训练网络提取到的图像多尺度特征，采用正半交嵌入特征降维方式减少冗余特征的影响。然后，通过多过程特征学习降低计算中的时间复杂度，提高训练效率。最后，根据训练模型得出待测图像的局部马氏距离，提高检测性能。相关实验表明，本方法在石板材数据集上的结果优于当前几种先进方法，同时在石板材表面缺陷检测和定位方面证明本方法的有效性。

Abstract:: The surface defect detection of slate is a challenging task, particularly for small defects like edge bumps and cracks. In addition, the existence of redundant features will influence the training effect, multiscale feature learning will require multidimensional calculation, and the calculation complexity will increase. Considering the above problems, this paper proposes a method for detecting surface defects in slate materials based on unsupervised learning to solve the problem in this task effectively. First, the semiorthogonal embedding feature dimension reduction is used on the multiscale features of the image extracted using a pretraining network to reduce the effect of redundant features. Further, the time complexity of calculation is reduced through multiprocess feature learning, increasing training efficiency. Finally, the local Markov distance of the image to be measured is obtained in accordance with the training model to improve the detection performance. Relevant experiments show that the results of this method on the slate data set are superior to several advanced methods at present, and the effectiveness of this method is verified by detecting and locating surface defects in slate materials.

参考文献/References:: [1] 马立修. 激光切割及其在切割石板材中的应用研究[J]. 应用激光, 2008, 28(4): 292–294
MA Lixiu. The laser cutting and its application in cutting the stone plate[J]. Applied laser, 2008, 28(4): 292–294
[2] SAKURADA M, YAIRI T. Anomaly detection using autoencoders with nonlinear dimensionality reduction[C]//Proceedings of the MLSDA 2014 2nd Workshop on Machine Learning for Sensory Data Analysis. Gold Coast: ACM, 2014: 4-11.
[3] 杨文元. 多标记学习自编码网络无监督维数约简[J]. 智能系统学报, 2018, 13(5): 808–817
YANG Wenyuan. Unsupervised dimensionality reduction of multi-label learning via autoencoder networks[J]. CAAI transactions on intelligent systems, 2018, 13(5): 808–817
[4] NGUYEN D T, LOU Z, KLAR M, et al. Anomaly detection with multiple-hypotheses predictions[EB/OL]. (2018-10-31)[2022-12-06]. https://arxiv.org/abs/1810.13292.
[5] AKCAY S, ATAPOUR-ABARGHOUEI A, BRECKON T P. GANomaly: semi-supervised anomaly detection via adversarial training[C]//Asian Conference on Computer Vision. Cham: Springer, 2019: 622-637.
[6] PIDHORSKYI S, ALMOHSEN R, ADJEROH D A, et al. Generative probabilistic novelty detection with adversarial autoencoders[C]//Proceedings of the 32nd International Conference on Neural Information Processing Systems. Montréal: ACM, 2018: 6823-6834.
[7] SABOKROU M, KHALOOEI M, FATHY M, et al. Adversarially learned one-class classifier for novelty detection[C]//2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Salt Lake City: IEEE, 2018: 3379-3388.
[8] YI Jihun, YOON S. Patch SVDD: patch-level SVDD for anomaly detection and segmentation[C]//Asian Conference on Computer Vision. Cham: Springer, 2021: 375-390.
[9] RUDOLPH M, WANDT B, ROSENHAHN B. Same same but DifferNet: semi-supervised defect detection with normalizing flows[C]//2021 IEEE Winter Conference on Applications of Computer Vision. Waikoloa: IEEE, 2021: 1906-1915.
[10] BERGMAN L, COHEN N, HOSHEN Y. Deep nearest neighbor anomaly detection[EB/OL]. (2020-02-10) [2022-12-06]. https://arxiv.org/abs/2002.10445.
[11] COHEN N, HOSHEN Y. Sub-image anomaly detection with deep pyramid correspondences[EB/OL]. (2020- 05-02) [2022-12-06]. https://arxiv.org/abs/2005.02357.
[12] DENG Jia, DONG Wei, SOCHER R, et al. ImageNet: a large-scale hierarchical image database[C]//2009 IEEE Conference on Computer Vision and Pattern Recognition. Miami: IEEE, 2009: 248-255.
[13] RUFF L, VANDERMEULEN R, GOERNITZ N, et al. Deep one-class classification[C]//35th International Conference on Machine Learning. Stockholm: PMLR, 2018, 80: 4393-4402.
[14] BERGMAN L, HOSHEN Y. Classification-based anomaly detection for general data[EB/OL]. (2020-05-10) [2022-12-06]. https://www.researchgate.net/publication/341175574_Classification-Based_Anomaly_Detection_for_General_Data.
[15] NAPOLETANO P, PICCOLI F, SCHETTINI R. Anomaly detection in nanofibrous materials by CNN-based self-similarity[J]. Sensors, 2018, 18(2): 209.
[16] BERGMANN P, FAUSER M, SATTLEGGER D, et al. Uninformed students: student-teacher anomaly detection with discriminative latent embeddings[C]//2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Seattle: IEEE, 2020: 4182-4191.
[17] LEE K, LEE K, LEE H, et al. A simple unified framework for detecting out-of-distribution samples and adversarial attacks[C]//Proceedings of the 32nd International Conference on Neural Information Processing Systems. Montréal: ACM, 2018: 7167-7177.
[18] DEFARD T, SETKOV A, LOESCH A, et al. PaDiM: A patch distribution modeling framework for anomaly detection and localization[C]//International Conference on Pattern Recognition. Cham: Springer, 2021: 475-489.
[19] ROTH K, PEMULA L, ZEPEDA J, et al. Towards total recall in industrial anomaly detection[C]//2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition. New Orleans: IEEE, 2022: 14298-14308.
[20] JOHNSON W B, LINDENSTRAUSS J. Extensions of lipschitz mappings into a Hilbert space[J]. Contemporary mathematics, 1984, 26(1): 189–206.
[21] CHOROMANSKI K, ROWLAND M, WELLER A. The unreasonable effectiveness of structured random orthogonal embeddings[C]//Proceedings of the 31st International Conference on Neural Information Processing Systems. Long Beach: ACM, 2017: 218-227.
[22] LEZAMA J, QIU Qiang, MUSé P, et al. OLE: orthogonal low-rank embedding, A plug and play geometric loss for deep learning[C]//2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Salt Lake City: IEEE, 2018: 8109-8118.
[23] SALEHI M, SADJADI N, BASELIZADEH S, et al. Multiresolution knowledge distillation for anomaly detection[C]//2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Nashville: IEEE, 2021: 14897-14907.
[24] MAHALANOBIS P C. On the generalised distance in statistics[EB/OL]. (2016-08-15) [2022-12-06]. http://bayes.acs.unt.edu:8083/BayesContent/class/Jon/MiscDocs/1936_Mahalanobis.pdf.
[25] KIM J H, KIM D H, YI S, et al. Semi-orthogonal embedding for efficient unsupervised anomaly segmentation[EB/OL]. (2021-05-31)[2022-12-06]. https://arxiv.org/abs/2105.14737.pdf
[26] MEZZADRI F. How to generate random matrices from the classical compact groups[J]. Notices of the AMS, 2006, 54(5): 592–604.
[27] HE Kaiming, ZHANG Xiangyu, REN Shaoqing, et al. Deep residual learning for image recognition[C]//2016 IEEE Conference on Computer Vision and Pattern Recognition. Las Vegas: IEEE, 2016: 770-778.
[28] GUDOVSKIY D, ISHIZAKA S, KOZUKA K. CFLOW-AD: real-time unsupervised anomaly detection with localization via conditional normalizing flows[C]//2022 IEEE/CVF Winter Conference on Applications of Computer Vision. Waikoloa: IEEE, 2022: 1819-1828.

备注/Memo

收稿日期:2022-12-7。
作者简介:王延春秋,硕士研究生,主要研究方向为无监督学习、图像缺陷检测;葛泉波,教授,博士生导师,主要研究方向为智能电网大数据分析、人机混合系统智能评估、无人系统协同优化理论与方法、工程信息融合理论与方法。主持国家自然科学基金重点项目1项,发表学术论文100余篇;刘华平,教授,博士生导师,中国人工智能学会理事、中国人工智能学会认知系统与信息处理专业委员会秘书长,吴文俊人工智能科学技术奖获得者,主要研究方向为机器人感知、学习与控制、多模态信息融合。主持国家自然科学基金重点项目2项,发表学术论文340余篇
通讯作者:刘华平.E-mail:hpliu@tsinghua.edu.cn

更新日期/Last Update: 1900-01-01

石板材表面缺陷检测的无监督学习方法 PDF下载HTML

备注/Memo

石板材表面缺陷检测的无监督学习方法

PDF下载 HTML