The project began in November 2017 and led to the launch of APRIL™ Eye, the world’s first artificial intelligence-based vision system. By combining machine learning with artificial intelligence, it’s able to read anything that is also legible to the naked eye, with just a basic camera and scanner backed by a ‘brain’, making it a much more cost-effective solution. The system takes a photo of each date code, and then reads them back using scanners to ensure they match the programmed date code for that product run. The production line comes to a complete stop if a date code doesn’t match, ensuring that no incorrect labels can be released into the supply chain. What’s more, manufacturers benefit from comprehensive reporting and full traceability without relying on paper checks carried out by operators.
Vision systems have previously relied on the kind of standardised printing that can only be achieved with optical character recognition (OCR). Unfortunately, due to retailers’ needs to adapt fonts and formats, OCR printing isn’t suitable for the industry. Inkjet printers have the flexibility to meet these needs but there is an extremely variable output, which means it can be difficult for the date code to be read by a traditional vision system.
OAL has used over half a million photos of variations of date codes to ‘teach’ the system to recognise numbers and letters, whatever the format, and with a large amount of variability, in terms of different fonts and sizes, font distortion and packing changes with switching product runs, as well as lighting and heat sensitivity. In this way, food manufacturers can rely on the system to offer the level of security vision systems can achieve in other industries.
Where APRIL Eye is installed, it verifies the date codes on over 1,000 products a minute, ranging from fresh produce to ready meals for a number of large, multinational food manufacturers. Following its installation on packaging lines, those with APRIL Eye are yet to experience a withdrawal. By incorporating APRIL Eye on to packaging line, manufacturers can remove operators and achieve full automation and unmanned operations, eliminating product recalls caused by human error.