Researcher Anil Jain and team have developed LemurFaceID, which identifies lemurs with 98.7% accuracy for humane tracking of the endangered species.
A team of biologists and computer scientists at the Michigan State University have developed a facial recognition system for lemurs, paving the way for better long-term tracking data to aid conservation strategies.
Anil Jain, biometrics expert and university distinguished professor at Michigan State University, and his team modified their human facial recognition system to create LemurFaceID, the first computer facial recognition system that correctly identifies more than 100 individual lemurs with 98.7% accuracy.
Figure 1: Anil K. Jain (Source: MSU)
“Like humans, lemurs have unique facial characteristics that can be recognised by this system,” Jain said. “Once optimised, LemurFaceID can assist with long-term research of endangered species by providing a rapid, cost-effective and accurate method for identification.”
Jain used 462 images of 80 red-bellied lemurs and 190 images of other lemur species to create the dataset for the facial recognition system. Many of the photos were taken in Ranomafana National Park in Madagascar by study co-authors Rachel Jacobs, of George Washington University, and Stacey Tecot, of University of Arizona.
For short-term studies of lemurs, researchers often rely on “soft” identifiers to recognise individual lemurs, such as differences in body size and shape or the presence of injuries and scars. However, relying on variations in appearance can make it difficult for different researchers studying lemurs to identify the same lemur over time. This means there are few long-term studies of lemur populations.
“Studying lemur individuals and populations over long periods of time provides crucial data on how long individuals live in the wild, how frequently they reproduce, as well as rates of infant and juvenile mortality and ultimately population growth and decline,” Tecot said. “Using LemurFaceID can inform conservation strategies for lemurs, a highly endangered group of mammals.”
LemurFaceID also provides a more humane, non-invasive way to identify lemurs. “Capture and collar” methods are commonly used to identify wild lemurs but these methods can cause injury or stress and are costly because of veterinary services and anaesthesia.
Researchers said LemurFaceID also may be used to assist in other forms of animal conservation. Lemurs, among many other endangered animals, are illegally captured and kept as pets. LemurFaceID could provide law enforcement, tourists and researchers with a tool to rapidly report sightings and identify captive lemurs, which would help with conservation efforts.
In addition, Jain believes LemurFaceID can be used to identify other primate and non-primate species with variable facial hair and skin patterns, such as bears, red pandas, raccoons or sloths. Doing so may assist conservation of the world’s primates, half of which are facing extinction.
“Facial recognition technology has the potential to help safeguard our society,” Jain said. “Adapting it to help save endangered species is one of its most inspiring uses.”