Science Technology Leafsnap Is a New App to Identify Trees By Bonnie Alter Writer University of Toronto Bonnie Alter covered the sustainability and design scene for TreeHugger in London and the UK. our editorial process Bonnie Alter Updated October 11, 2018 Migrated Image Share Twitter Pinterest Email Science Space Natural Science Technology Agriculture Energy It's a TreeHugger's dream come true. Leafsnap is a new free app that identifies trees. Go for a walk, take a shot of a leaf and this little wonder will identify its tree and give all kinds of information about it. The app is a result of a collaboration between Columbia University, the University of Maryland and the Smithsonian Institution. The computer scientists made use of mathematical techniques developed for face recognition and they applied these to species identification. The botanists at the Smithsonian collected the initial data sets of leaf species and the photography. Every leaf photograph that is uploaded is matched against a leaf-image library so that the best matches are ranked and noted for verification. It is complicated because "within a single species, leaves can have quite diverse shapes, while leaves from different species are sometimes quite similar, so one of the main technical challenges in using leaves to identify plant species has been to find effective representations of their shape, which capture their most important characteristics." It's not perfect...yet. The leaf identification process needs work. You have to take a picture of the leaf against a white background, which is a bit awkward when you are marching around. It is only good for the USA, although the Canadian Hemlock is noted. That tree could come in handy right now for some Canadians. And for this TreeHugger, the snapshot part wouldn't work at all. However, there is a nice visual dictionary of leaf types which can be matched to names and descriptions if one has the patience to scroll through it. There are photos and information about the tree's flowers, fruit, seeds and bark--giving the user a very full understanding of the species.