Food and Beverage Case Code Reading
Read codes and date lots on case packaging against varying backgrounds
Graphical programming environment for deep learning-based industrial image analysis
Consumer food and beverage products such as ice cream, beer and other items increasingly distinguish themselves by case printing design customized in response to season, special events, new product formulations, time-limited promotions, and market targeting. Such products have date, lot code, and other specific tracking codes printed on the cases that need to be read to manage the supply chain.
Unreadable codes lead to supply chain problems, incorrect deliveries, inadequate supplies of required product, and consumer dissatisfaction.
To reliably read the characters, conventional optical character recognition (OCR) must be programmed for each specific case background. As backgrounds proliferate and change more quickly this programming task imposes significant delays, as well as leading to increased errors.
AI-powered OCR tools read printed codes on challenging backgrounds. The OCR tool is easily set up and deployed thanks to a pretrained font library. It then trains on a small set of images of text printed on a variety of backgrounds and can learn to identify text while ignoring background variations, even when text is presented on a newly introduced background that was not part of the original training set. The fact that the OCR tool does not require retraining when text appears on novel backgrounds keeps the production line working without any interruption or reduction in read accuracy.
Food and beverage cases are reliably routed to the designated customers, regardless of changes in package design.