A facial recognition application for dogs developed to fight rabies

A new mobile phone-based facial recognition app for dogs has the potential to significantly improve rabies vaccination efforts in endemic areas like Africa and Asia, according to research published in the journal Scientific reports.

Led by researchers at Washington State University, a team used the app to test its effectiveness at a rabies vaccination clinic in rural Tanzania, where they microchipped, vaccinated and recorded the dogs.

The technology proved remarkably accurate on a subsequent visit to surrounding villages, once poor images and poorly recorded information were removed from its database. Thanks to the application, operators identified 76.2% of vaccinated dogs and 98.9% of unvaccinated dogs.

“As domestic dogs are the primary reservoir for human rabies, controlling human rabies on a global scale requires mass vaccination of dogs,” said WSU Associate Professor Felix Lankester, principal investigator of the study. .

“When doing mass vaccination, one of the major problems we face is trying to identify which dogs have and have not been vaccinated. For example, microchips are too expensive to use scale needed to eliminate rabies, and collars can be removed by owners. We developed this app to see if facial recognition could work, and it shows great promise in helping us achieve that goal.

Rabies kills around 60,000 people each year. Almost all cases occur in Africa and Asia, and more than 99% are due to dog bites. Systematic and consistent vaccination efforts, such as those conducted by WSU’s Rabies Free Africa program, are effective in controlling the disease, but approximately 40% of dogs in an area must be vaccinated at any one time to achieve herd immunity and prevent prolonged transmission of the virus. The ability to accurately and efficiently identify vaccinated dogs is therefore essential to the success of rabies elimination programs.

The facial recognition algorithm used in the app, developed in collaboration with PiP My Pet, a company based in Vancouver, Canada, and researchers at WSU’s Paul G. Allen School for Global Health, identifies a dog by examining key components of his face and comparing to images of other dogs’ faces in his previously stored image archive. Images with the highest number of similar components are returned as possible matches and the user must decide if there is a match.

The application depends on image quality and information about each dog, including age, color and gender, being correctly recorded. Before poor quality images and incorrect information were removed from the database, users were only able to match 65% of vaccinated dogs.

Lankester, who is also director of Rabies Free Africa, said the effectiveness of the app could be improved with better technology, such as newer smartphones with high-quality cameras, and additional operator training.

In addition to its potential as a tool for identifying vaccinated dogs, the technology holds promise for use in other species, in disease control efforts, and for research purposes where it may be necessary to identify animals.

Currently, users must be online to operate the face matching component. However, Lankester said the team is also working to compress the size of the “engine” that drives the app’s matching feature to allow it to be downloaded and used offline, which would reduce the app’s dependency Internet access, which is not always available in the most remote areas.

“We’re not there yet, but I think with investment the technology can get there. I’m excited about its potential,” Lankester said, “but we need to find funds to invest to move it forward I look forward to people contacting us if they have ideas for funding or would like to collaborate on this.