March 3, 2017

In Madagascar, a new technology will help keep track of the east African island’s famous long-tailed, furry inhabitants (and cute human cousins): lemurs. To help identify and study the endangered animals, a team of lemur experts and computer scientists has developed a lemur facial recognition system. The biometric system, called LemurFaceID, uses computers to analyze photographs and video much like other systems that identify people. LemurFaceID differentiates the animals according to their eyes and skin patterns, while also noting body size or shape and the presence of scars or injuries.

LemurFaceID can tell this handsome lemur apart from the other lemurs in its jungle neighborhood. Credit: © Shutterstock

Scientists classify lemurs, along with human beings, apes, and monkeys, as primates. Lemurs live only in Madagascar and Comoros, a small island group between Madagascar and the African mainland. Because of hunting and habitat loss, the animals are critically endangered. Tracking lemurs in the wild helps scientists learn more about the animals’ habits and life cycles. Scientists can then develop fine-tuned conservation strategies to protect the animals. Identifying lemurs in the wild also helps people spot animals illegally captured to be sold as pets.

A zookeeper feeds ring-tailed lemurs at the Nyíregyháza Zoo in Hungary. Ring-tailed lemurs are threatened by hunting and habitat destruction in their native Madagascar. Credit: © Attila Kisbenedek, AFP/Getty Images

Anil Jain, a computer science and engineering professor at Michigan State University, developed LemurFaceID with the help of a team of scientists and graduate students. The team fed hundreds of images of wild lemurs into the system, which correctly identified individuals 98.7 percent of the time. Jain and his team published the results of their lemur facial recognition study last month in the journal BioMed Central Zoology.

Once applied, LemurFaceID will use automated cameras to photograph lemurs in their natural habitats. Use of the facial recognition system will cut down drastically on the cost, time, and effort of tracking lemurs in the wild. Previous tracking largely relied on researchers trapping and individually tagging each animal—a tried-and-true method, but quite costly and time consuming, and distressing for the lemurs as well. With LemurFaceID, the animals will only have to “say cheese” for the camera and then scamper on their way. Researchers can then keep track of the animals simply by turning on their computers (and maintaining the cameras, of course).

After LemurFaceID proves itself in the wild, the technology may be adjusted for the study of other animals, particularly those with variable facial hair and skin patterns such as bears, raccoons, red pandas, and sloths.