The customised metal box, a premium reusable and recyclable packaging solution, is one of Massilly’s flagship products. It is now inspected using a vision solution comprising two levels of AI, developed and integrated by Psycle. Patrice Ferrero and Emeline Lautissier deployed this solution on the production line; they tell us about their experience.
Why two levels of AI?
Patrice Ferrero: We needed to automate inspection on a line that processes a multitude of designs. The human eye can detect a defect in a design element, whereas a simple camera is less capable of doing so. We absolutely needed an intelligent system. We started by working on defect detection, which is the most complex issue, using supervised learning AI. Then we added a simpler level for decor analysis. This allows us to reduce the learning time required before each OF.
Why Psycle?
PF: From the very first tests carried out at Psycle, it seemed to me that their AI could meet our needs. This was confirmed when we worked at our premises, with a system made available to us for validation testing.
Psycle AI allows us to choose what we want to detect, and to detect it without false positives.
What is the user feedback?
Emeline Lautissier: Line operators are autonomous when it comes to adjusting cameras and launching learning processes at the start of the OF. The Psycle solution is accessible on their usual screen and easy to use. The quality department, for its part, regularly feeds new annotated images into the defect detection algorithm. The process is very smooth.
It was a great project, and a discovery of AI-assisted vision that went very well thanks to the support of Natan and Baptiste.