Please use this identifier to cite or link to this item:
Publisher DOI: 10.1016/j.procir.2022.05.115
Title: Procedural synthetic training data generation for AI-based defect detection in industrial surface inspection
Language: English
Authors: Schmedemann, Ole  
Baaß, Melvin 
Schoepflin, Daniel  
Schüppstuhl, Thorsten  
Keywords: Synthetic training data; machine learning; surface inspection; industrial quality control; domain randomization
Issue Date: 26-May-2022
Publisher: Elsevier
Source: Procedia CIRP 107: 1101-1106 (2022)
Abstract (english): 
Supervised machine learning methods are increasingly used for detecting defects in automated visual inspection systems. However, these methods require large quantities of annotated image data of the surface being inspected, including images of defective surfaces. In industrial contexts, it is difficult to collect the latter since acquiring sufficient image data of defective surfaces is costly and time-consuming. Additionally, gathered datasets tend to contain selection-bias, e.g. under representation of certain defect classes, and therefore result in insufficient training data quality. Synthetic training data is a promising alternative as it can be easily generated unbiasedly and in large quantities. In this work, we present a procedural pipeline for generating training data based on physically based renderings of the object under inspection. Defects are being introduced as 3D-models on the surface of the object. The generator provides the ability to randomize object and camera parameters within given intervals, allowing the user to use the domain randomization technique to bridge the domain gap between the synthetic data and the real world. Experiments suggest that the data generated in this way can be beneficial to training defect detection models.
Conference: 55th CIRP Conference on Manufacturing Systems, CIRP CMS 2022 
DOI: 10.15480/882.4365
ISSN: 2212-8271
Journal: Procedia CIRP 
Institute: Flugzeug-Produktionstechnik M-23 
Document Type: Article
Project: Verfahren zur automatischen Qualitätskontrolle mittels robotergeführten Videoendoskopen 
Funded by: Bundesministerium für Wirtschaft und Klimaschutz (BMWK) 
More Funding information: This research was funded by the German Federal Ministry for Economic Affairs and Climate Action under grant number ZF4736301LP9.
Peer Reviewed: Yes
License: CC BY-NC-ND 4.0 (Attribution-NonCommercial-NoDerivatives) CC BY-NC-ND 4.0 (Attribution-NonCommercial-NoDerivatives)
Appears in Collections:Publications with fulltext

Files in This Item:
File Description SizeFormat
1-s2.0-S2212827122003997-main.pdf720,7 kBAdobe PDFView/Open
Show full item record

Page view(s)

Last Week
Last month
checked on Dec 5, 2022


checked on Dec 5, 2022

Google ScholarTM


Note about this record

Cite this record


This item is licensed under a Creative Commons License Creative Commons