Surface Defect Detection and Root Cause Analysis

Authors

  • Tianchen Liu

  • Fan Zhu

  • Haoran Yu

  • Haisong Gu

artificial intelligence, deep neural networks(DNN), DataonomyTM, defect detection, root cause finding

Abstract

Artificial Intelligence has played an increasingly important role in surface defect detection in recent years. At the same time, there are many challenges using deep learning for this area, such as the detection accuracy, shortage of data and, lack of knowledge of root cause of defects. To solve the problem of data shortage, we propose a taxonomy method called Dataonomy TM to extend a meta defect datasets with a small number of samples for training defect classifiers. For the accuracy, we apply two latest deep neural network(DNN) architectures, Inception v3 and fully convolutional networks (FCN) so as not only to classify whether there are defects but also to make a pixel-wise prediction to inference the areas of defects. For those detected defects, we combine DNN with traditional AI methods to find root causes of detected defects. We use a generalized multi-image matting algorithm to extract common defects automatically. We apply this technology to identify defects that stem from systematic errors in the surface operation. Experimental results have shown great capability and versatility of our proposed methods.

How to Cite

References

Nhat-Duc Hoang (2018) Nhat-Duc Hoang, An Artificial Intelligence Method for Asphalt Pavement Pothole Detection Using Least Squares Support Vector Machine and Neural Network with Steerable Filter-Based Feature Extraction, Hindawi, Advances in Civil Engineering, Volume 2018, Article ID 7419058. 2018(1), 7419058. https://doi.org/10.1155/2018/7419058

Ssurabh Ghatnekar Ssurabh Ghatnekar, Use Machine Learning to Detect Defects on the Steel Surface, op/articles/use-machine-learning-to-detect-defects- on-the-steel-surface. https://software.intel.com/content/www/us/en/develop/articles/use-machine-learning-to-detect-defects-on-the-steel-surface.html

Amir Zamir, Alexander Sax, William Shen, Leonidas Guibas, Jitendra Malik, Silvio Savarese (2018) Taskonomy: Disentangling Task Transfer Learning. 3712-3722. https://doi.org/10.1109/cvpr.2018.00391

Koki Muto, Takuma Matsubara, Hiroyasu Koshimizu (2018) Proposal of local feature vector focusing on the differences among neighboring ROI's. 1-3. https://doi.org/10.1109/iwait.2018.8369637

Z. Yu, X. Wu, X. Gu (2017) In: Liu, M., Chen, H., Vincze, M (eds.) ICVS 2017 LNCS, vol. 1052, 417-426.

Ren R, Hung T, Tan KC (2017) 2017 A generic deeplearning-based approach for automated surface inspection. 99, 1-12.

Hongbin Jia (2005) Surface defect detection, classification and root cause diagnosis in steel hot rolling process.

Xu, Y. Zhu, K. Sun, D. Wang, H. GU (2018) 2018 Visual Defect Inspection Across Industry.

Christian Szegedy, Vincent Vanhoucke, Sergey Ioffe, Jon Shlens, Zbigniew Wojna (2016) 2016 Rethinking the inception architecture for computer vision. 2818-2826. https://doi.org/10.1109/cvpr.2016.308

R. Saaty (1987) 1987 The analytic hierarchy processwhat it is and how it is used. 9(3-5), 161-176. https://doi.org/10.1016/0270-0255(87)90473-8

Math Works Math Works, /examples/office-assignments-by-binary-integerprogramming. https://www.mathworks.com/help/optim/examples/office-assignments-by-binary-integer-programming.html

Zhiyang Yu, Xiaojun Wu, Xiaodong Gu Zhiyang Yu, Xiaojun Wu, and Xiaodong Gu, Fully Convolutional Networks for Surface Defect Inspection in Industrial Environment.

(2015) Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks. 91-99.

(2010) In: 2010 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 2528-2535.

(2017) https://hci.iwr.uni-heidelberg.de/node/3616

Daniel Weimer, Bernd Scholz-Reiter, Moshe Shpitalni (2016) Design of deep convolutional neural network architectures for automated feature extraction in industrial inspection. 65(1), 417-420. https://doi.org/10.1016/j.cirp.2016.04.072

F. Timm, E. Barth (2011) Non-parametric texture defect detection using Weibull features. 7877.

Surface Defect Detection and Root Cause Analysis

Published

2020-07-20

How to Cite

Surface Defect Detection and Root Cause Analysis. (2020). Global Journal of Science Frontier Research, 20(31), 1-8. https://www.journalofscience.org/index.php/GJSFR/article/view/2748