Composite score for anomaly detection in imbalanced real-world industrial dataset

Résultats de recherche: Contribution à un journal/une revueArticleRevue par des pairs

17 Téléchargements (Pure)

Résumé

In recent years, the industrial sector has evolved towards its fourth revolution. The quality control domain is particularly interested in advanced machine learning for computer vision anomaly detection. Nevertheless, several challenges have to be faced, including imbalanced datasets, the image complexity, and the zero-false-negative (ZFN) constraint to guarantee the high-quality requirement. This paper illustrates a use case for an industrial partner, where Printed Circuit Board Assembly (PCBA) images are first reconstructed with a Vector Quantized Generative Adversarial Network (VQGAN) trained on normal products. Then, several multi-level metrics are extracted on a few normal and abnormal images, highlighting anomalies through reconstruction differences. Finally, a classifier is trained to build a composite anomaly score thanks to the metrics extracted. This three-step approach is performed on the public MVTec-AD datasets and on the partner PCBA dataset, where it achieves a regular accuracy of 94.65% and 87.93% under the ZFN constraint.

langue originaleAnglais
journalMachine Learning
Les DOIs
Etat de la publicationPublié - 20 nov. 2023

Empreinte digitale

Examiner les sujets de recherche de « Composite score for anomaly detection in imbalanced real-world industrial dataset ». Ensemble, ils forment une empreinte digitale unique.

Contient cette citation