Researchers at
Columbia Engineering, led by Computer Science Professor Peter Belhumeur have
developed Birdsnap, a new iPhone app which enables users to identify bird
species through uploaded photos. It is an electronic field guide featuring 500
of the most common North American bird species. The researchers used computer
vision and machine learning techniques to develop the app.
Birdsnap not only
identify species, but can also identify which parts of the bird the algorithm
uses to identify each species. Next on
the agenda of the researchers is to add ability to recognize bird songs,
bringing audio and visual recognition together.
This is indeed
great news for birders. If researchers from other parts of the world work on
these lines, in another 10 years time we will have a wonderful compendium from
across the world. Technology can certainly come in handy in our pursuit of
better tools for managing wildlife.
No comments:
Post a Comment