GanoDIP - GAN Anomaly Detection through Intermediate Patches: a PCBA Manufacturing Case

Arnaud Bougaham, Adrien Bibal, Isabelle Linden, Benoit Frenay
Proceedings of the Third International Workshop on Learning with Imbalanced Domains: Theory and Applications, PMLR 154:104-117, 2021.

Abstract

Industry 4.0 and recent deep learning progress make it possible to solve problems that traditional methods could not. This is the case for anomaly detection that received a particular attention from the machine learning community, and resulted in a use of generative adversarial networks (GANs). In this work, we propose to use intermediate patches for the inference step, after a WGAN training procedure suitable for highly imbalanced datasets, to make the anomaly detection possible on full size Printed Circuit Board Assembly (PCBA) images. We therefore show that our technique can be used to support or replace actual industrial image processing algorithms, as well as to avoid a waste of time for industries.

Cite this Paper

BibTeX
@InProceedings{pmlr-v154-bougaham21a, title = {GanoDIP - GAN Anomaly Detection through Intermediate Patches: a PCBA Manufacturing Case}, author = {Bougaham, Arnaud and Bibal, Adrien and Linden, Isabelle and Frenay, Benoit}, booktitle = {Proceedings of the Third International Workshop on Learning with Imbalanced Domains: Theory and Applications}, pages = {104--117}, year = {2021}, editor = {Moniz, Nuno and Branco, Paula and Torgo, Luis and Japkowicz, Nathalie and Woźniak, Michał and Wang, Shuo}, volume = {154}, series = {Proceedings of Machine Learning Research}, month = {17 Sep}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v154/bougaham21a/bougaham21a.pdf}, url = {https://proceedings.mlr.press/v154/bougaham21a.html}, abstract = {Industry 4.0 and recent deep learning progress make it possible to solve problems that traditional methods could not. This is the case for anomaly detection that received a particular attention from the machine learning community, and resulted in a use of generative adversarial networks (GANs). In this work, we propose to use intermediate patches for the inference step, after a WGAN training procedure suitable for highly imbalanced datasets, to make the anomaly detection possible on full size Printed Circuit Board Assembly (PCBA) images. We therefore show that our technique can be used to support or replace actual industrial image processing algorithms, as well as to avoid a waste of time for industries.} }
Endnote
%0 Conference Paper %T GanoDIP - GAN Anomaly Detection through Intermediate Patches: a PCBA Manufacturing Case %A Arnaud Bougaham %A Adrien Bibal %A Isabelle Linden %A Benoit Frenay %B Proceedings of the Third International Workshop on Learning with Imbalanced Domains: Theory and Applications %C Proceedings of Machine Learning Research %D 2021 %E Nuno Moniz %E Paula Branco %E Luis Torgo %E Nathalie Japkowicz %E Michał Woźniak %E Shuo Wang %F pmlr-v154-bougaham21a %I PMLR %P 104--117 %U https://proceedings.mlr.press/v154/bougaham21a.html %V 154 %X Industry 4.0 and recent deep learning progress make it possible to solve problems that traditional methods could not. This is the case for anomaly detection that received a particular attention from the machine learning community, and resulted in a use of generative adversarial networks (GANs). In this work, we propose to use intermediate patches for the inference step, after a WGAN training procedure suitable for highly imbalanced datasets, to make the anomaly detection possible on full size Printed Circuit Board Assembly (PCBA) images. We therefore show that our technique can be used to support or replace actual industrial image processing algorithms, as well as to avoid a waste of time for industries.
APA
Bougaham, A., Bibal, A., Linden, I. & Frenay, B.. (2021). GanoDIP - GAN Anomaly Detection through Intermediate Patches: a PCBA Manufacturing Case. Proceedings of the Third International Workshop on Learning with Imbalanced Domains: Theory and Applications, in Proceedings of Machine Learning Research 154:104-117 Available from https://proceedings.mlr.press/v154/bougaham21a.html.

Related Material