Friday, 30 May 2014

Crow or raven? Birdsnap app tells you what bird you snapped - Delhi Daily News

Debarjun Saha | 11:11 |

As you see the birds flutter by when you are in a park or on a picnic, it can be difficult for you to know exactly which creature you have spotted.

But computer scientists have now developed an app, which can identify a bird from a single picture. Computer vision and machine learning techniques have been used to create Birdsnap. A team of researchers led by Professor Peter Belhumeur at Columbia Engineering, New York City developed the app.

The free iPhone app claims to be an electronic field guide offering 500 of the most common North American bird species. The app allows the users to recognize bird species by uploading photos. There is also a website, which contains 50,000 pictures and bird calls for every species.

The users can sort through species alphabetically, by their relationship in the Tree of Life and by the regularity with which they are seen at a particular place and season. It is designed to discover visually alike species and gives graphic suggestions for how to distinguish among the birds.

The app and the website were developed with the University of Maryland. They were introduced at the EEE Conference on Computer Vision and Pattern Recognition in Columbus, Ohio.

Professor Belhumeur and fellow computer scientist David Jacobs of the University of Maryland, comprehended that many of the techniques they have developed for face recognition, could also be practical and applicable to automatic species identification.

Face recognition algorithms depend on approaches that discover correspondences between similar parts of different faces, so that, for example, a nose is compared to a nose.

Birdsnap works in the same manner by noticing the parts of a bird to inspect the graphic resemblance of its comparable parts. Each species is categorized through the location of 17 parts. Birdsnap, by design, find out visually alike species and gives visual suggestions for how they can be d istinguished.

The team is also using the fact that smartphone cameras embed the date and location in their images to improve classification accuracy. The team by using the fact that smartphone cameras embed the date and location in their pictures to improve classification precision have designed a system that can identify which birds are arriving, departing, or migrating.



via Science - Google News http://ift.tt/SYOt4Q

IFTTT

Put the internet to work for you.

Turn off or edit this Recipe

No comments:

Post a Comment

Twitter Delicious Facebook Digg Stumbleupon Favorites More

Search