When observant life behavior in a very natural setting, researchers usually need to keep their distance, making it difficult to identify individual animals and track their movements and activity over time.
One new technique recently developed for observing red-bellied lemurs takes a hi-tech approach to long-distance identification, using changed facial-recognition software.
Biologists collaborated with computer engineers to adapt software designed to acknowledge human faces, making a new program dubbed LemurFaceID, that they described during a new study. The software detects distinctive features in lemur faces so that researchers can pinpoint people even in the absence of features such as scars or injuries, and without causing the lemurs undue stress that comes with capture.
Previously, the most correct means of identifying individual lemurs involved trappings and tagging the animals. but LemurFaceID only needs a frontal-view photo of a lemur’s face — a lemur “mug shot” — that is then uploaded to a information and analyzed by algorithms tailored to figure on lemur faces, evaluating variability in facial hair patterns and in alternative unique facial expression.
Highly accurate facial tracking
Using LemurFaceID, scientists assembled a information from 462 images of eighty known red-bellied lemurs living in Madagascar’s Ranomafana national park. In a hundred trials, the software correctly identified individual lemurs from images with nearly 98 % accuracy, the researchers reported.
“We demonstrate that the LemurFaceID system identifies individual primates with grade of accuracy that means facial-recognition technology could be a potential great tool for semipermanent analysis on wild lemur populations,” the study authors wrote on-line February. seventeen within the journal BioMed Central biological science.
LemurFaceID offers a means for scientists to quickly verify if newly sighted lemurs are unique, and could help scientists track long-term people over the long term. The software might even track lemurs that have been poached and sold illegally, study co-author rachel Jacobs, a biological anthropologist with the center for the Advanced Study of paleobiology at The George Washington University, said in a very statement.
Facial-recognition software like LemurFaceID could even be applied to other species that have similar variations in the patterns of their facial hair and skin — for example, red pandas, sloths, bears and raccoons — and could cut back the danger of injury that animals face from traditional capture and collar ways, the researchers wrote in their journal article.
“We see lots of different potential applications for this,” study co-author Stacey Tecot, an professor at the University of Arizona school of anthropology, said within the statement. “This is just the primary step for us in taking this in many directions.