Communications of the ACM
Is It a Crow or a Raven? New Birdsnap App Will Tell You!
The Birdsnap smartphone app provides access to an electronic field guide to 500 of the most common North American bird species.
Credit: Birdsnap
Columbia University researchers led by professor Peter Belhumeur have developed Birdsnap, a smartphone app that uses computer vision and machine-learning techniques to produce an electronic field guide featuring 500 of the most common North American bird species.
Birdsnap, which enables users to identify bird species through uploaded photos, is linked to a website that includes about 50,000 images. Birdsnap also features birdcalls for each species, and offers users several ways to organize species.
"Our goal is to use computer vision and artificial intelligence to create a digital field guide that will help people learn to recognize birds," Belhumeur says.
Birdsnap works similar to facial-recognition technologies in that it detects the parts of a bird so that it can examine the visual similarity of its comparable parts. The app automatically finds visually similar species and makes visual suggestions for how they can be distinguished.
"What's really exciting about Birdsnap is that not only does it do well at identifying species, but it can also identify which parts of the bird the algorithm uses to identify each species," Belhumeur says.
The researchers also developed part-based one-versus-one features, each of which classifies birds of just two species, based on a small part of the body of the bird.
From Columbia University
View Full Article
Abstracts Copyright © 2014 Information Inc., Bethesda, Maryland, USA
No entries found