Skip to main content

Birds: an Interactive Field Guide

Visipedia

An experimental iPad app identifies most North American birds, with a little help from a human user. The app is essentially an interactive field guide, where computer vision algorithms analyze user-submitted bird photos, ask questions and display images and information about bird species that are likely matches.

Computer science professor Serge Belongie is leading the project, which is part of a larger move to fill a gap in the world of online search. While text-driven search, such as Google and Wikipedia, has been wildly successful, identifying images has so far proven much more difficult.

Jacobs School computer scientists are working with UC Berkeley and Caltech as well as Cornell's Laboratory of Ornithology, which contributed images of more than 500 North American species of birds.

Belongie hopes the app will ignite a movement among other enthusiasts, who will partner with computer scientists to create similar apps for everything from flowers, to butterflies, to lichens and mushrooms.

Learn more at: visipedia.org

Print Article