Cats and their “poker faces”: Artificial intelligence decodes facial expressions

Research project
Cats and their “poker faces” – artificial intelligence decodes the animals’ facial expressions

A typical “poker face”: Cats are masters at hiding their emotions and, if possible, not showing weakness.

© Ingimage / Imago Images

Reading emotions on a cat’s face is very difficult. In the future, artificial intelligence could help interpret animals’ facial expressions – for example, to find out whether they are in pain.

When cats suffer from an illness, their owners often recognize it quite late. Because the animals are true masters at this, Pains to hide and not show any signs of weakness. Some experts even speak of a “poker face”.

Could in the future Artificial intelligence (AI) help with early diagnosis: In a joint project, researchers from Germany and Israel are currently working on AI programs that analyze cats’ faces to find signs of pain. The experts hope to develop practical help for veterinary medicine and also for private individuals, for example in the form of apps that can be used to photograph and analyze cat faces.

It has long been known that cats’ faces show signs of discomfort. The animals show a “pain face”, meaning changes can be seen, for example in their facial expressions and the position of their ears. Such behavior is also known from other animals, such as rabbits. But the deviations from a “normal” facial expression are minimal and not easy to interpret.

Software is trained on cat facial expressions

People need a lot of practice and experience to read the “pain faces” of animals. Human assessments are also often subjective. A team of experts from AI and the Veterinary medicine has developed two algorithms in the past few months that are intended to use facial expression analysis to determine whether cats are currently feeling pain. This is reported by several scientific media outlets and the research institutes involved.

“Artificial intelligence (AI) offers great opportunities to better recognize pain in cats and to carry out treatments more gently,” writes the Hannover Veterinary University. The institution’s foundation (TiHo) and the Information Systems Department of the University of Haifa in Israel are collaborating on this project.

The new AI programs are currently able to correctly interpret pets’ facial expressions in up to 77 percent of cases, the website “Spektrum.de” reported this week, citing an exclusive translation from the specialist journal “Scientific American”.

“The AI ​​can see more than the naked human eye because it reacts sensitively to subtle details,” quotes “Spektrum.de” the Israeli computer scientist Anna Zamansky.

As with other AI programs, the international team initially needed a lot of data to feed the software. According to reports, more than 80 cats were photographed at the Hannover Veterinary University Foundation. The animals were of different ages and had different diseases.

New software already has a fairly high hit rate

Two different AI programs analyzed facial expressions, such as the tension of the facial muscles. The researchers compare the results of the AI ​​with the clinical data they collected about the animals.

One of the two programs had a hit rate of 65 percent for detecting pain in animal faces, the other 77 percent, according to the descriptions of the research, which was reported on last summer. “AI systems offer us a huge opportunity in veterinary practice to improve the care of cats,” said Professor Sabine Kästner, who is involved in the project.

What was exciting for the team was that the nose and mouth regions in particular played a role in the mechanical pain classification, as the Hanover scientists say in the description of their research. The position of the ears, which was actually taken into account in the “pain face” and other classifications, is less important.

The researchers now hope to develop everyday programs for cat owners and veterinarians. However, it is not yet clear when veterinarians will be able to treat their patients using such AI-supported methods.

Sources: “Spektrum.de“, Hanover University of Veterinary MedicineScientific Reports“, “Scientific American

Read at stern+: A professor writes about genetics and field research – and in the case of Jonathan B. Losos, the result is an exciting non-fiction book. Animal lovers find out how the cat once came “from the savannah to the sofa”.

source site-1