All PET bottles are marked with an expiry date. Everyone knows that. However, the quality of the marking can vary depending on the speed of the production line and the technology selected. Conventional image processing software copes well with these markings if the bottle color, speed and contents are the same. However, if there are variations, then this software reaches its limits.
However, deep learning software has no problem with variations. Thanks to this software, manufacturers can reduce the costs of fine-tuning and maintaining the image processing system. The deep learning software is trained to automatically adapt to new variations. This means that the results are completely independent of the bottle color, the marking quality and the color of the contents.
This software basically has the ability to see and make decisions like a human being. This reduces waste as there are fewer incorrect results.
The OCR tool used is based on the artificial intelligence of the Retina Deep Learning solution. With this tool, more than 50,000 parts/hour can be read with a reading rate of 99.99%. The developer of the software, 3HLE, is very confident of this data and guarantees these figures to customers.
This demo video shows a typical OCR application in the food and beverage industry. The marking is on transparent, colored and curved PET surfaces.
Conventional OCR tools were able to achieve a read rate of 95% in this application, but only with one liquid. This result was only achieved after a few days of fine-tuning and other tricks. It is important that even poorly legible characters are recognized.
The Retina OCR tool, on the other hand, achieved a read rate of 99.99% within just a few hours, without any confusion.
Would you like to test this tool with your application? Then please contact us.
CONTACT
Our experts will be happy to help you. Get in touch with us!
