New app identifies and assesses cattle health by facial recognition


Researchers from the Brazilian Agricultural Research Corporation (EMBRAPA), Dairy Cattle, and the Federal University of Juiz de Fora (UFJF) recently announced the creation of an app that identifies cattle by face and is also able to assess their health status based on the database information collected by users. The software, called Happy Cow ID, uses computer vision and machine learning. It works like the human brain. Using deep learning and neural networks, the software “learns” as it is exposed to the animals.

The technology creates patterns as it recognizes features of cattle faces and categorizes the animals according to race, posture, and health status. Dairy farmers from all over the country were invited to help and speed up the process by uploading images of their cows.

According to the developers, it can be a cheaper, faster, and more accurate system to replace earrings and chips. Compared to the rings currently used on farms, the app has a few advantages. It does not need to be replaced in case of loss or damage, and its price does not vary according to changes in the dollar exchange rate.

Earrings application is also more demanding, requiring each animal to be immobilized to place the identifiers and to read the data. These practices cause stress and injuries, in addition to increasing the risk of illnesses.

The app promises greater control and easier handling of the herd. It will also help farm administration since it will be possible to store all animals’ information on computers or smartphones.

The app is expected to be launched in 2022 and will be available to producers around the world.