Abstract
Finding and implementing a suitable machine learning (ML) solution to a task at hand has several facets. The technical side of ML has widely been discussed in detail, see, e. g., (Heizmann, M., A. Braun, M. Hüttel, C. Klüver, E. Marquardt, M. Overdick and M. Ulrich. 2020. Artificial Intelligence with Neural Networks in Optical Measurement and Inspection Systems. at – Automatisierungstechnik 68(6): 477–487). This contribution focusses on the industrial implementation issues of ML projects, particularly for machine vision (MV) tasks. Especially in small and medium-sized enterprises (SMEs), resources cannot be activated at will in order to use a new technology like ML. We take this into account by, on the one hand, helping to realistically evaluate the opportunities and challenges involved in implementing ML projects for a given task. On the other hand, we consider not only technical aspects, but also organizational, social and customer-related ones. It is discussed which know-how a company itself has to bring into an ML project and which tasks can also be performed by service providers. Here, it becomes clear that ML techniques can be used at different levels of detail. The question of “make or buy” is therefore also an entrepreneurial one when introducing ML into one’s own products and processes, and must be answered with a view to one’s own possibilities and structures.
About the authors
Michael Heizmann is Professor of Mechatronic Measurement Systems at the Institute of Industrial Information Technology at the Karlsruhe Institute of Technology. His research interests include machine vision, signal and image processing, image and information fusion, measurement technology, machine learning, artificial intelligence and their applications in industry.
Alexander Braun is Professor of Physics at the University of Applied Sciences in Düsseldorf. Formerly he was responsible for the optical quality of mass produced ADAS cameras at a Tier 1. His research areas focus on physical-realistic simulation of camera systems for ADAS/AD, numerical accuracy and fundamental limits of optical models, computer vision and machine learning, and optical metrology.
Markus Glitzner is a Research Engineer at MVTec Software GmbH. His research covers the field of machine learning for industrial image processing. Until 2019 he was part of a project integrating real-time magnetic resonance imaging into radiotherapy at University Medical Center Utrecht.
Matthias Günther is deputy director of the Fraunhofer Institute for Digital Medicine MEVIS in Bremen and head of imaging devices. He is Professor of Physics at the University Bremen and his expertise includes medical imaging basics, magnetic resonance imaging, ultrasound imaging, biophysical modelling, and data-driven image-reconstruction using deep learning technology.
Günther Hasna is leading the team of sensor and photonics experts at Ansys Germany GmbH and participating as Sensor Experts in research programs of autonomous driving. He was studying Mechatronics at the University of Applied Physics in Munich. After 5 years in TEMIC working on optoelectronic sensors, he was joining OPTIS in France extending his skillset to simulation. Since OPTIS has been acquired by ANSYS several years ago he was extending his working field to radar sensors and HF simulation.
Christina Klüver is a private lecturer of Soft Computing at the Institute of Computer Science and Business Administration at the University of Duisburg-Essen. Her research areas include methods of Artificial Intelligence and Artificial Life for the analysis of complex systems.
Jakob Krooß studied Medical Engineering Science at the University of Lübeck. He is currently working on his doctorate at the Helmut Schmidt University in Hamburg. His research areas include machine vision and real time image processing for detection and localization of fast running processes.
Erik Marquardt studied electrical engineering at RWTH Aachen University. There he did his doctorate on an optical measurement system. He worked in industry for 15 years, mainly in machine vision companies, before joining the Association of German Engineers (Verein Deutscher Ingenieure e. V., VDI) in 2012. Since then he has been working with experts in technical committees on the development of VDI standards for optical measurement systems and additive manufacturing.
Michael Overdick is responsible for the Technology Management at SICK AG, a supplier of sensors and sensor systems for the entire field of industrial automation. Until 2009 he was in charge of the research activities of Philips in the field of medical X-ray imaging, comprising all components of the imaging chain including the medical image processing.
Markus Ulrich is Professor of Machine Vision Metrology at the Institute of Photogrammetry and Remote Sensing at the Karlsruhe Institute of Technology. His research areas include machine vision, close-range photogrammetry, image processing, machine learning and their applications in industry.
Acknowledgment
The authors would like to thank Andreas Frommknecht, Markus Hüttel, Jonathan Krauß, Marco Müller-ter Jung, Tobias Nagel and Philipp Reusch for their contribution to the VDI status report “Machine Learning in SME” [12], which is an essential basis for this contribution.
References
1. Deutsche Akademie der Technikwissenschaften (acatech). 2021. KI im Mittelstand – Potenziale erkennen, Voraussetzungen schaffen, Transformation meistern. https://www.acatech.de/publikation/ki-im-mittelstand-potenziale-erkennen-voraussetzungen-schaffen-transformation-meistern/.Search in Google Scholar
2. European Commission. 2020. White Paper on Artificial Intelligence – A European approach to excellence and trust. https://ec.europa.eu/info/sites/info/files/commission-white-paper-artificial-intelligence-feb2020_en.pdf.Search in Google Scholar
3. European Commission. 2021. A European approach to Artificial intelligence. https://digital-strategy.ec.europa.eu/en/policies/european-approach-artificial-intelligence.Search in Google Scholar
4. European Commission. 2021. Proposal for a Regulation of the European Parliament and of the Council Laying down Harmonised Rules on Artificial Intelligence (Artificial Intelligence Act) and Amending Certain Union Legislative Acts. https://eur-lex.europa.eu/legal-content/EN/TXT/?qid=1623335154975&uri=CELEX%3A52021PC0206.Search in Google Scholar
5. Evaluation of measurement data – Guide to the expression of uncertainty in measurement. 2018.Search in Google Scholar
6. Heizmann, M., A. Braun, M. Hüttel, C. Klüver, E. Marquardt, M. Overdick and M. Ulrich. 2020. Artificial Intelligence with Neural Networks in Optical Measurement and Inspection Systems. at – Automatisierungstechnik 68(6): 477–487.10.1515/auto-2020-0006Search in Google Scholar
7. Kersten, W. and S. Lodemann. 2019. What impact does AI have on SME processes and employees? – An insight into supply chain management. https://www.hamburg-logistik.net/fileadmin/user_upload/blog/bilder/Veranstaltungen/VA_LIHH/do.innovation/2019/E_-_TUHH_doinnovation.pdf.Search in Google Scholar
8. Koopman, P. 2018. The heavy tail safety ceiling. SAE Automated and Connected Vehicle Systems Testing Symposium, Greenville, USA, June 2018. https://users.ece.cmu.edu/~koopman/pubs/koopman18_heavy_tail_ceiling.pdf.Search in Google Scholar
9. Krauß, J., J. Dorißen, H. Mende, M. Frye and R. H. Schmitt. 2019. Machine learning and artificial intelligence in production: Application areas and publicly available data sets. In: (J. P. Wulfsberg, W. Hintze and B.-A. Behrens, eds) Production at the leading edge of technology. Springer, pp. 493–501.10.1007/978-3-662-60417-5_49Search in Google Scholar
10. Su, J., D. V. Vargas and K. Sakurai. 2019. One pixel attack for fooling deep neural networks. IEEE Transactions on Evolutionary Computation 23(5): 828–841.10.1109/TEVC.2019.2890858Search in Google Scholar
11. VDI Verein Deutscher Ingenieure e. V. 2019. Gesellschaft für Mess- und Automatisierungstechnik, Fachbereich Optische Technologien. Maschinelles Lernen – Neuronale Netze in optischen Mess- und Prüfsystemen, VDI-Statusreport (in German). https://www.vdi.de/ueber-uns/presse/publikationen/details/kuenstliche-intelligenz-mit-neuronalen-netzen-in-optischen-mess-und-pruefsystemen.Search in Google Scholar
12. VDI Verein Deutscher Ingenieure e. V. 2020. Gesellschaft für Mess- und Automatisierungstechnik, Fachbereich Optische Technologien. Maschinelles Lernen in KMU – Künstliche Intelligenz im eigenen Unternehmen nutzen, VDI-Statusreport (in German). https://www.vdi.de/ueber-uns/presse/publikationen/details/vdi-statusreport-maschinelles-lernen-in-kmu.Search in Google Scholar
13. VDI/VDE/VDMA 2017. 2632 Part 3: 2017-10 Machine vision/industrial image processing – Acceptance test of classifying machine vision systems. Beuth Verlag, Berlin.Search in Google Scholar
14. VDI/VDE/VDMA. 2020. 2632 Part 3.1: 2020-08 Machine vision/industrial image processing – Acceptance test of classifying machine vision systems – Test of classification performance. Beuth Verlag, Berlin.Search in Google Scholar
© 2022 Walter de Gruyter GmbH, Berlin/Boston
