Facial recognition software could help save endangered lemurs

February 20, 2017, 3:02 p.m.
Three lemurs
Photo: Andrea Izzotti/Shutterstock

Facial recognition software normally is used to identify humans, but it's being put to work in a new way: identifying individual lemurs to assist in conservation research of this endangered species.

Typically, lemur studies rely on body size, shape, scars or other identifiers to recognize individuals. This isn't always the most easy or accurate way. Placing GPS collars on them makes it easier to track them, but it adds stress and the risk of injury into the mix.

This software, on the other hand, could be a far more reliable way to identify for certain an individual lemur without such invasive study methods. Studies are critical for lemur conservation, as lemurs are the most endangered primate group in the world.

"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," University of Arizona researcher Stacey Tecot told PhysOrg. "Using LemurFaceID can inform conservation strategies for lemurs, a highly endangered group of mammals."

But research isn't the only potential use for this new technology. PhysOrg reports:

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.

Just how accurate is the software in identifying individuals?

According to a study testing the software, "We trained and tested our system using images from wild red-bellied lemurs (Eulemur rubriventer) collected in Ranomafana National Park, Madagascar. Across 100 trials, with different partitions of training and test sets, we demonstrate that the LemurFaceID can achieve 98.7% ± 1.81% accuracy (using 2-query image fusion) in correctly identifying individual lemurs."

Such a high degree of accuracy is impressive, and also very important to knowing that it will be useful and reliable for scientists in the field as well as conservationists protecting animals from the pet trade.