Reading pigs’ emotions could speed up disease treatments
Technology which can detect emotion on pigs’ faces could help farmers identify and treat sick animals before illnesses really take hold.
Scientists at Scotland’s Rural College (SRUC) and the University of the West of England (UWE) are developing facial recognition software which can detect different emotions in pigs.
They hope by monitoring animals’ faces within a herd, they will be able to spot health and welfare problems sooner, reducing the need for costlier treatments further down the line.
Having previously proven that pigs signal their intentions to other pigs through facial expressions, the researchers are currently looking at the expressions pig show when they are in pain or under stress.
By capturing 3D and 2D facial images of breeding sows in typical commercial situations, the scientists hope to identify pigs’ reactions in different emotional states.
For example, lame sows can show different facial expressions when they are in pain and once they have been given pain relief, SRUC scientists said.
Images of pigs are being processed at UWE, with the researchers developing machine learning techniques to enable them to automatically identify emotions conveyed by different expressions.
Once the techniques have been verified, the scientists will develop technology for on-farm use, enabling producers to monitor individual sows within a herd.
SRUC senior researcher Emma Baxter, PhD, said identifying health issues early gives farmers the chance to improve herd health by tackling problems quickly.
“This will reduce production costs by preventing impact of health issues on performance,” she said.
“By focusing on the pig’s face, we hope to deliver a truly animal-centric welfare assessment technique where the animal can ‘tell’ us how it feels,” she added.
“This allows insight into both short-term emotional reactions and long-term individual ‘moods’ of animals under our care.”
Posted on October 23, 2019