I came across something cool today – LemurFaceID.
A new facial recognition programme developed by Michigan State University has managed to correctly identity different lemurs through photographs of their faces with a staggering 98% accuracy.
Conservationists currently have to carry out their research by capturing wild animals by the use of tranquilizers and humane traps, and sticking microchips in them or attaching cumbersome tracking collars. This very rarely causes any lasting harm but it can – unsurprisingly – distress the animals in the short term. New technology is being utilized in various ways by conservation scientists – for examples, drones for following migratory species, GPS trackers for locating illegal poaches – to improve our knowledge and enable us to better protect endangered species.
Jain (the brains behind LemurFaceID) used a dataset of roughly 462 images of 80 red-bellied lemurs, taken in Madagascar’s Ranomafana National Park, and 190 images of other lemur species to train a facial recognition system, called LemurFaceID. “Training” entails feeding image data through an algorithm that calculates variations between pixels. Each pixel is a string of 1s and 0s, so these algorithms yield mathematically unique patterns, or solutions, that distinguish a face, or a lemur, from one another.