The fight against rabies is going hi-tech with a new mobile phone-based facial recognition application expected to improve vaccination efforts in endemic areas in Africa.

The app, which is currently being tested in rural Tanzania, has demonstrated potential in effectively managing and eradicating rabies.

During vaccination clinics, dogs are microchipped, vaccinated, and registered. The facial recognition app proved to be remarkably accurate, successfully identifying 76.2 percent of vaccinated dogs and 98.9 percent of unvaccinated dogs during subsequent visits to surrounding villages.

The app’s facial recognition algorithm, developed in collaboration with PiP My Pet, a company based in Vancouver, Canada, and researchers at Washington State University’s Paul G. Allen School for Global Health, identifies dogs by analysing key components of their faces and comparing them to previously stored images.

Read: How clayen fridge will allow better rabies vaccine storage

Verification

The app returns images with the highest number of similar components as possible matches, which the user then verifies.

The study, testing novel facial recognition technology to identify dogs during vaccination campaigns, published in the journal Scientific Reports, highlights the potential of this technology in countries struggling with rabies in Africa and Asia.

Human rabies is mainly caused by domestic dogs, making mass dog vaccination essential for global rabies control. However, identifying vaccinated dogs during mass vaccinations is a significant challenge. Traditional methods like microchipping are expensive, and collars removed by owners.

While the primary focus of the app is identifying vaccinated dogs for rabies control, it also holds potential for use in other species, disease control efforts, and research purposes where animal identification is necessary.

The facial recognition app offers a promising solution to this problem.

Systematic and consistent vaccination efforts, like those led by WSU’s Rabies Free Africa program, are effective at controlling the disease, but approximately 40percent of dogs in an area must be vaccinated at any one time to achieve herd immunity and prevent sustained virus transmission. This makes the ability to accurately and efficiently identify vaccinated dogs vital for successful rabies elimination programs.

Read: Researchers use App in the fight against rabies

“Because domestic dogs are the main reservoir for human rabies, controlling human rabies globally requires the mass vaccination of dogs,” WSU Associate Professor Felix Lankester, the principal investigator of the study, said.

Lankester, who also serves as a director of Rabies Free Africa added, “When carrying out mass vaccination, one of the major problems that we face is trying to identify which dogs have and haven’t been vaccinated. For example, microchips are too expensive to use at the scales needed to eliminate rabies, and collars can be removed by owners. We developed this app to see if facial recognition might work, and it’s showing great promise in helping us to achieve that goal.”

To achieve optimal results, the app relies on high-quality images and accurate information about each dog, including its age, color, and sex.

To further enhance the app’s effectiveness, the researchers suggest using newer smartphones with high-quality cameras and providing additional operator training.

Although the app currently requires an internet connection for facial matching, the research team is working on compressing the app’s matching engine to make it downloadable and usable offline. This development would make the app more accessible in remote areas with limited internet access.

While the primary focus of the app is identifying vaccinated dogs for rabies control programs, it also holds potential for use in other species, disease control efforts, and research purposes where animal identification is necessary.