Researchers at UC San Diego, UC Berkeley, and Caltech have designed an iPad app that is able to identify most North American birds “with a little help from a human user.”
The interactive field guide asks users questions to find a match to the picture they’ve uploaded. The system will provide more accurate results the more people use it.
We chose birds for several reasons: there is an abundance of excellent photos of birds available on the Internet, the diversity in appearance across different bird species presents a deep technical challenge and, perhaps most importantly, there is a large community of passionate birders who can put our system to the tes.”
— Serge Belongie, computer scientist and project lead, Jacobs School of Engineering, UC San Diego
The app uses computer vision algorithms to analyze a picture submitted by a user, asks questions, and calls up images and information about a likely match.
The ornithology lab at Cornell has contributed a database of images of more than 500 North American species.
We are helping Visipedia reach an audience of birders who are hungry for this kind of technology.”
— Jessie Barry, researcher, Cornell Lab of Ornithology
The ultimate goal of the research is to find better ways to search images on the web.
How is technology changing your life for the better?
Request a demo version of the app: http://visipedia.org.
© Tony Leininger and IT for Good 2012. See sidebar for full copyright notice.