The Cornell Lab of Ornithology, along with Cornell Tech and Caltech, has developed a system that can recognize and identify bird species. The Merlin Bird Photo ID can currently identify 400 species, based on imagery examination, Wired
Birds are traditionally hard for recognition tools to identify.
“Asking computers to identify bird species is a challenge not only because some species look so alike, but also because their shape varies from moment to moment. On top of that, photographs of birds often include complex backgrounds, and the birds may be far away or blurry,” the Cornell Lab told Wired.
The team at Cornell and Caltech were determined to develop the tool, however, and did so by building a “visual recognition engine for birds,?Wired reports. This involved collecting a large amount of data and creating a complex algorithm that uses that data to identify various patterns, which in turn help the Merlin Bird Photo ID better identify each species. Part of the data included myriad photos of birds, accurately tagged, which Cornell received in droves.
At this time, Merlin Bird Photo ID is not 100 percent accurate, but the team is optimistic, and is looking forward to turning the tool into an app for avid bird watchers and bird lovers.
“Ultimately, we hope that Merlin will be a useful tool to identify birds from around the world ?and that its technology will be used to identify other wildlife, plants and objects too,” the research team told Wired.
Previous: OSU To Release Owl Back To Wild
Love this article? Check these out!