Artificial intelligence could be used to improve animal welfare, according to new research by experts at the University of Wageningen in the Netherlands.
The team has developed a “real-time facial expression recognition platform” – called WUR Wolf – that can code the emotions of farm animals.
The programme can recognise and evaluate 14 facial features combinations and seven emotional states of cows and pigs, according to lead author Suresh Neethirajan. If a cow’s eye whites are clearly visible, the animal could be excited or stressed. When a pig’s ears go forward it can be a sign of aggression.
“The input of data includes such things as the appearance of eyes, ear position/posture, age, orbital cheek or snout tightening, nose bulge, eyelid movement and the animal’s body and tail postures that a computer programme will need to mull over before giving an analysis of emotion,” he wrote in a piece for Pig Progress.
From these data, the researchers can infer the emotional states, including whether the animal is aggressive, calm or neutral. It’s far from straightforward, but the concept has the potential to detect illness or disease early.
Neethirajan told New Scientist that continuous monitoring by cheap cameras hooked up to a cloud-based system could be far better than the occasional visits by welfare auditors. He also said that rather than reducing animals’ pain and distress, positive states could be boosted.
“Emotions sensing offers a vast amount of potential for improving animal welfare and animal-human interactions,” the researchers wrote in their paper for the journal Sensors.