To solve this challenge in paper recycling plants, the system needs to evolve from a static system to a dynamic system which can rapidly reconfigure to handle different materials. Deep Learning offers the possibility to use vision-based algorithms based on combinations of complex features such as shape, form, colour and can be easily reconfigured to recognize new products.
A big challenge in paper recycling is the separation of cardboard from paper. Small pieces of cardboard cannot be sorted out of the waste paper and cause dirt spots and visible brown fibres in the recycled paper.
Within the AUTOWARE Project, imec and Robovision created a detection framework that can swiftly change between the materials as well as to train as fast as possible to quickly adapt for different types of cardboard.
Read more about the case here.