Abstract
Visual defect detection is critical to ensure the quality of most products. However, the majority of small and medium-sized manufacturing enterprises still rely on tedious and error-prone human manual inspection. The main reasons include: 1) the existing automated visual defect detection systems require altering production assembly lines, which is time consuming and expensive 2) the existing systems require manually collecting defective samples and labeling them for a comparison-based algorithm or training a machine learning model. This introduces a heavy burden for small and medium-sized manufacturing enterprises as defects do not happen often and are difficult and time-consuming to collect. Furthermore, we cannot exhaustively collect or define all defect types as any new deviation from acceptable products are defects. In this paper, we overcome these challenges and design a three-stage plug-and-play fully automated unsupervised 360\(^\circ \) defect detection system. In our system, products are freely placed on an unaltered assembly line and receive 360\(^\circ \) visual inspection with multiple cameras from different angles. As such, the images collected from real-world product assembly lines contain lots of background noise. The products face different angles. The product sizes vary due to the distance to cameras. All these make defect detection much more difficult. Our system use object detection, background subtraction and unsupervised normalizing flow-based defect detection techniques to tackle these difficulties. Experiments show our system can achieve 0.90 AUROC in a real-world non-altered drinkware production assembly line.
Z. Kuang and L. Ying—Equal contributions.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Patel, N., Mukherjee, S., Ying, L.: EREL-Net: a remedy for industrial bottle defect detection. In: Basu, A., Berretti, S. (eds.) ICSM 2018. LNCS, vol. 11010, pp. 448–456. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-04375-9_39
Ma, N., Zhu, X.: Computational stoning method for surface defect detection (2013)
Varun Chandola, A.B., Kumar, V.: Anomaly detection: a survey, no. 15 August 2009. https://dl.acm.org/doi/abs/10.1145/1541880.1541882
Chalapathy, R., Chawla, S.: Deep learning for anomaly detection: a survey (2019)
Bergmann, P., Fauser, M., Sattlegger, D., Steger, C.: MVTec AD - a comprehensive real-world dataset for unsupervised anomaly detection. In: 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2019)
Zhang, C.: Surface defect detection, segmentation and quantification for concrete bridge assessment using deep learning and 3d reconstruction (2020)
Vijayalakshmi, M.N., Senthilvadivu, M.: Performance evaluation of object detection techniques for object detection. In: 2016 International Conference on Inventive Computation Technologies (ICICT) (2016)
Lu, Y., Zhang, L., Xie, W.: Yolo-compact: an efficient yolo network for single category real-time object detection. In: 2020 Chinese Control and Decision Conference (CCDC) (2020)
Felzenszwalb, P.F., Girshick, R.B., McAllester, D., Ramanan, D.: Object detection with discriminatively trained part-based models. IEEE Trans. Pattern Anal. Mach. Intell. 32(9), 1627–1645 (2010)
Girshick, R.: Fast R-CNN. In: Proceedings of the IEEE International Conference on Computer Vision (ICCV), December 2015
Jocher, G., et al.: ultralytics/yolov5: v5.0 - YOLOv5-P6 1280 models, AWS, Supervise.ly and YouTube integrations (2021). https://doi.org/10.5281/zenodo.4679653
Bouwmans, B.H.T., Porikli, F., Vacavant, A.: Statistical models for background subtraction. In: Background Modeling and Foreground Detection for Video Surveillance, pp. 153–172 (2014)
Rashid, M., Thomas, V.: A background foreground competitive model for background subtraction in dynamic background. Procedia Technol. 25, 536–543 (2016)
Ronneberger, O., Fischer, P., Brox, T.: U-net: convolutional networks for biomedical image segmentation (2015)
Lin, S., Ryabtsev, A., Sengupta, S., Curless, B., Seitz, S., Kemelmacher-Shlizerman, I.: Real-time high-resolution background matting (2020)
Sengupta, S., Jayaram, V., Curless, B., Seitz, S., Kemelmacher-Shlizerman, I.: Background matting: the world is your green screen (2020)
Bergmann, P., Löwe, S., Fauser, M., Sattlegger, D., Steger, C.: Improving unsupervised defect segmentation by applying structural similarity to autoencoders (2019). http://dx.doi.org/10.5220/0007364503720380
Nachman, B., Shih, D.: Anomaly detection with density estimation. Phys. Rev. D 101, 075042 (2020). https://link.aps.org/doi/10.1103/PhysRevD.101.075042
Rudolph, M., Wandt, B., Rosenhahn, B.: Same same but DifferNet: semi-supervised defect detection with normalizing flows (2020)
Dinh, L., Sohl-Dickstein, J., Bengio, S.: Density estimation using real NVP (2017)
Trappenberg, T.P.: Machine learning with sklearn. In: Fundamentals of Machine Learning, pp. 38–65 (2019)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Kuang, Z., Ying, L., Tie, X., Jin, S. (2022). Normalizing Flow Based Defect Detection with Motion Detection. In: Berretti, S., Su, GM. (eds) Smart Multimedia. ICSM 2022. Lecture Notes in Computer Science, vol 13497. Springer, Cham. https://doi.org/10.1007/978-3-031-22061-6_1
Download citation
DOI: https://doi.org/10.1007/978-3-031-22061-6_1
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-22060-9
Online ISBN: 978-3-031-22061-6
eBook Packages: Computer ScienceComputer Science (R0)