KIT | KIT-Bibliothek | Impressum | Datenschutz

Deep Learning Strategies for Industrial Surface Defect Detection Systems

Martin, Dominik ORCID iD icon; Heinzel, Simon; Kunze von Bischhoffshausen, Johannes; Kühl, Niklas ORCID iD icon

Abstract:

Deep learning methods have proven to outperform traditional computer vision methods in various areas of image processing. However, the application of deep learning in industrial surface defect detection systems is challenging due to the insufficient amount of training data, the expensive data generation process, the small size, and the rare occurrence of surface defects. From literature and a polymer products manufacturing use case, we identify design requirements which reflect the aforementioned challenges. Addressing these, we conceptualize design principles and features informed by deep learning research. Finally, we instantiate and evaluate the gained design knowledge in the form of actionable guidelines and strategies based on an industrial surface defect detection use case. This article, therefore, contributes to academia as well as practice by (1) systematically identifying challenges for the industrial application of deep learning-based surface defect detection, (2) strategies to overcome these, and (3) an experimental case study assessing the strategies' applicability and usefulness.


Preprint §
DOI: 10.5445/IR/1000137893
Cover der Publikation
Zugehörige Institution(en) am KIT Institut für Wirtschaftsinformatik und Marketing (IISM)
Karlsruhe Service Research Institute (KSRI)
Publikationstyp Proceedingsbeitrag
Publikationsjahr 2022
Sprache Englisch
Identifikator KITopen-ID: 1000137893
Erschienen in Proceedings of the Hawaii International Conference on Systems Sciences (HICSS-55)
Veranstaltung 55th Hawaii International Conference on System Sciences (HICSS 2022), Online, 03.01.2022 – 07.01.2022
Schlagwörter surface defect detection, design science research, deep learning, industry 4.0
Nachgewiesen in arXiv
KIT – Die Forschungsuniversität in der Helmholtz-Gemeinschaft
KITopen Landing Page