Your browser doesn't support javascript. This means that the content or functionality of our website will be limited or unavailable. If you need more information about Vinnova, please contact us.

Digital classification of beef

Reference number
Coordinator EUROP System of Sweden AB - Patronen Workspace
Funding from Vinnova SEK 869 548
Project duration June 2021 - November 2023
Status Completed
Venture Innovative Startups
Call Innovative Startups step 2 spring 2021

Important results from the project

In Sweden and within EU all beef is classified according to the EU´s official classification system - EUROP. It is also used as a basis for payment for the meat. Today, the classification is done manually at the slaughterhouses with specially trained personnel under the control of The Swedish Board of Agriculture. Our project has developed a product for digital automation of the classification process. The method is based on camera technology, image processing and artificial intelligence (AI). The system reduces the need for visual inspection and increases objectivity in classification of the usability of the meat.

Expected long term effects

The tested equipment works well. The image quality of captured images works well. The imaging process has been refined during the project. Storage and sorting of the images has been quality assured. The images maintain a sufficiently high image quality without the large amounts of data inhibiting data transfer or the AI analysis. In order to ensure the quality of the more uncommon classification groups E and P-, the system will need to be further developed when more images of these are collected.

Approach and implementation

The project has had to be adapted to circumstances such as a pandemic and modification of image exposure to gather sufficient data for an AI training. After AI training, we can state that the system works and can be calibrated further with reasonable efforts to achieve the authorities´ eligibility requirements for quality assurance.

The project description has been provided by the project members themselves and the text has not been looked at by our editors.

Last updated 9 December 2023

Reference number 2021-01497