A multi-departmental team of psychologists and software developers from Queen’s University have developed an app called Petcentage which can identify the facial similarities between humans and their pet dogs and cats.
The old joke that people tend to look like their pets has a long history. Certainly, a morning walk in any of Belfast’s parks can give you plenty of food for thought. But a recent investigation by Queen’s researchers has suggested that this link make be stronger than we think, especially in cats and dogs. After a first stage study suggested that people find it surprisingly easy to match owners with their pets, the second stage was to discover whether facial recognition could go one step further.
The sophisticated face mapping tool, built using the Face API on Azure, can accurately measure the facial similarity between a person and their pet cat or dog with everything from eye shape to hair length being taken into consideration by the software. It will then attribute a petcentage score. Now that the software has been built, Queen’s are asking for volunteers to take part in the second stage of the study to map how much we look like our cats and dogs.
The Petcentage project was inspired by some previously published psychological studies suggesting that dogs really do look like their owners. It aimed to capitalise on that research in order to allow pet owners to use cutting edge technology to measure precisely to what extent they resembled their own pets.
Speaking about the success of the project, lead investigator Professor April McGill of the School of Psychology at Queen’s University said:
“Humans and their pets have a deep rooted connection that goes back millennia. We domesticated dogs and cats over 30,000 years ago and slowly we have bred these creatures to reflect our own ideals of beauty.
We wanted to investigate this link and also take it further. Why are we, as humans, drawn to certain breeds of cat or dog over others? Is it because we intrinsically recognise a similarity to ourselves? And if the naked eye can accurately match pets with their owners we were fascinated to see what facial recognition could really do.”
The project has, so far, focused on understanding the similarities between humans and their pet cats and dogs. However, the team behind it are hopeful that they will be able to use it on other animals. Further updates are expected to include facial recognition mapping for a wide variety of animals including horses, hamsters and parakeets.
Queen's University Belfast is committed to Equality, Diversity and Inclusion.
For more information please read our Equality and Diversity Policy.
Queen's University Belfast is registered with the Charity Commission for Northern Ireland NIC101788
VAT registration number: GB 254 7995 11