Machine Learning

Deep learning based computer vision - ROBOVISION has configured deep learning systems and associated tools to create novel machine vision systems, which are applied in the use-cases. More specifically, in a first phase, the machine learning system data needs to be collected related to the process. This data can be separated into two categories: human annotation (labels) and associated image data. Obtaining relevant labels is a costly process, for this ROBOVISION has developed solutions in its RVAI platform. In a second phase, the system needs to be trained, for which ROBOVISION uses the latest deep learning advances. This novel technology offers the possibility to use vision-based algorithms based on combinations of complex features such as shape, form, colour and can be reconfigured to recognize new products, as demonstrated in the STORA ENSO simulation use case.

Area of the technology

  • Machine and Deep Learning Applied
  • Vision Technology
  • Artificial Intelligence

Targeted Industrial Sectors

  • Recycling industry
  • Carton Sorting and Picking
  • Generalized anomaly detection to support process quality control

Technology Readiness level

TRL 7 - system prototype demonstration in operational environment

Contact Information