In Northwest Europe, assembly processes and services of manufacturers of high-tech systems are characterized by a high variety of products and solutions with low volume. Production automation, flexibility and optimization are essential processes to produce smaller series and at the same time realize the wide variety of products and services.
To enable labor productivity improvements, devices are increasingly equipped with vision systems for pick-and-place applications, quality controls, object localization and object recognition. Vision systems, however, are sensitive to changes in the environment, which can cause systems to shut down. Vision systems are particularly sensitive to unpredictable changes in the environment, such as lighting, shadow formation, product orientation and large optical variations in, for example, natural products.
Machine Learning (ML), a form of artificial intelligence, can largely solve these shortcomings and make vision systems more robust and faster to configure; ML is ideal for use in vision applications.
However, ML for vision is a far-from-my-bed show for many SMBs, destined for multinationals with large budgets. Above all, the structure and knowledge about applying ML for vision is neither clear nor easily accessible. Therefore, the research question is: How can industrial SMEs use machine learning frameworks within vision applications to realize more efficient production processes? The consortium wants to use this project to provide insight into this ML structure; secondly, to make ML available to SMEs; third, explore together how ML for Vision can be applied industrially in three cases and, fourthly, to secure and disseminate the knowledge gained within SMEs and education.
Topic
Computer vision, Machine learning, Data science.
Goals
The main focus is on developing and sharing knowledge about machine learning, deep learning and computer vision within the consortium. With this knowledge, (open) workshops are developed for the benefit of a generic platform for computer vision applications.
Partners
- Saxion
- NHL
- Clear Flight Solutions
- IMS, Malvern Panalytical
- PM Bearings
- Riwo
- Singa
- StadLandWater
- Timmerije
- Viro
- Boost
Duration
October 1, 2019 until October 1, 2021.
Financing
This project is funded by SIA RAAK-mkb.