Science Natural Science What's That Bird? New Website Identifies Species by Your Photo By Melissa Breyer Editorial Director Hunter College F.I.T., State University of New York Cornell University Melissa Breyer is Treehugger’s editorial director. She is a sustainability expert and author whose work has been published by the New York Times and National Geographic, among others. our editorial process Melissa Breyer Updated October 11, 2018 ©. Cornell University Share Twitter Pinterest Email Science Space Natural Science Technology Agriculture Energy Your computer just became an ornithologist. In a breakthrough for bird watchers and the avian-curious everywhere, the Visipedia research project and the Cornell Lab of Ornithology have collaborated on a nifty website that has a keen skill: it can identify hundreds of bird species by photo alone. Called Merlin Bird Photo ID, the identifier is capable of recognizing 400 of the mostly commonly encountered birds in the United States and Canada. "It gets the bird right in the top three results about 90 percent of the time, and it's designed to keep improving the more people use it," said Jessie Barry at the Cornell Lab of Ornithology. "That's truly amazing, considering that the computer vision community started working on the challenge of bird identification only a few years ago." The process is simple. A user uploads an image of a bird and enters in when and where the photo was taken; then the user draws a box around the bird and clicks on its bill, eye, and tail. Within seconds, presto. Merlin looks at the pixels and does some powerful artificial intelligence magic with millions of data points, then presents the most likely species, including photos and song. "Computers can process images much more efficiently than humans – they can organize, index, and match vast constellations of visual information such as the colors of the feathers and shapes of the bill," said Serge Belongie, a professor of Computer Science at Cornell Tech. "The state-of-the-art in computer vision is rapidly approaching that of human perception, and with a little help from the user, we can close the remaining gap and deliver a surprisingly accurate solution." Merlin's powers are the result of a lot of human work, as it has learned to recognize each species from tens of thousands of images identified and labeled by birders. It also relies on an excess of 70 million sightings recorded by bird enthusiasts in the eBird.org database, which it then narrows down using the location and time of year when the photo was taken. (So thank you, eBirders.) Although for now it can not be used with mobile devices – they are working on it. And once it is smartphone-ready, the team will add it to the Merlin Bird ID app. And then, you can have an ornithologist in your pocket as well.