Columbia University, the University of Maryland, and the Smithsonian Institution are working on visual recognition software to help identify species from photographs. Leafsnap is a series of electronic field guides being developed to demonstrate this new technology. This free mobile app helps identify tree species from photographs of their leaves and contains beautiful high-resolution images of their flowers, fruits, petioles, seeds, and bark. The high-resolution images in the original app were created by the conservation organization Finding Species.
The Original Leafsnap currently includes trees found in the Northeastern United States and Canada, and will soon grow to cover the trees of the entire continental United States.
Leafsnap UK includes trees from across the United Kingdom with species information and imagery provided by the Natural History Museum in London
Leafsnap turns users into citizen scientists, automatically sharing images, species identifications, and geo-coded stamps of species locations with a community of scientists who will use the stream of data to map and monitor the ebb and flow of flora.
The Leafsnap family of electronic field guides aims to leverage digital applications and mobile devices to build an ever-greater awareness of and appreciation for biodiversity. The City College of New York developed and tested curricular materials that use the Leafsnap app to help middle school students notice, group, and contextualize street trees in the patterns of evolution. Curricular guide and other educational materials are available from here.
The genesis of Leafsnap was the realization that many techniques used for face recognition developed by Professor Peter Belhumeur and Professor David Jacobs, of the Computer Science departments of Columbia University and the University of Maryland, respectively, could be applied to automatic species identification.
Professors Jacobs and Belhumeur approached Dr. John Kress, Research Botanist and Curator at the Smithsonian to start a collaborative effort for designing and building such a system for plant species. Columbia University and the University of Maryland designed and implemented the visual recognition system used for automatic identification. In addition, Columbia University designed and wrote the iPhone, and iPad apps, the leafsnap.com website, and wrote the code that powers the recognition servers. The Smithsonian was instrumental in collecting the datasets of leaf species and supervising the curation efforts throughout the course of the project. As part of this effort, the Smithsonian contracted the not-for-profit nature photography group Finding Species, which collected and photographed the high-quality photos available in the apps and the website. The newest version of Leafsnap has been expanded to include the trees of Canada through collaboration with the Canadian Wildlife Federation. A separate version for the trees of the United Kingdom is also available. UK species were collected and photographed by the Natural History Museum, London, UK. Click on "Species" above to browse Leafsnap’s gallery of species. (Leafsnap UK species are not included here.)
For press inquiries, please email [email protected].
The first time you take a photo, it automatically creates an account for you, after which you can go to the options screen and change your username and/or password.
Simply "swipe" across the result to mark it as that species.
Simply "swipe" across the image on the collection page to delete it.
Photos of leaves must be taken with a single leaf on a fully-white background for our automatic algorithms to find them. Also, keep in mind that the app must first send the image to our servers for processing, and so you must have a working internet connection when you press "Snap It!" No internet connection is required to browse through the rest of the field guide, however.
We have one under development, but since the app is free and the work is being done by volunteers, we do not have a release date, nor a firm guess as to when this will be.
We are working to first complete coverage of the Northeast US, then the rest of the United States, and finally the rest of the world.
Neeraj Kumar is leading the software development effort.
Priyank Singh worked on improving the leaf identification algorithms.
Weikang Wan is building an automated tool for data curation.
Chun-Kang Chen is automating the backend processing pipeline.
Ila Agrawal helped with leaf identification.
Peter Belhumeur supervises the Columbia team.
Guangyu Sun is investigating new leaf identification algorithms.
Vinay Kumar stress-tested the backend and worked on database management.
Gaurav Agrawal explored the use of SIFT for leaf recognition.
Haibin Ling designed the original leaf recognition algorithm and participated in the development of the initial electronic field guide (EFG) prototype.
David Jacobs supervises the University of Maryland team.
Aditya Malik is working on image segmentation for leaves.
Angjoo Kanazawa is working on improving the leaf recognition algorithm.
Joao Soares is working on image segmentation for leaves.
Arijit Biswas is working on improving the leaf identification algorithms.
Daozheng Chen has worked on speeding up the recognition code.
Daniel Grant is a long-term volunteer in the Smithsonian Botany Department. He assists with specimen and image data processing.
Ida C. Lopez is the project coordinator at Smithsonian. She also led the collection expedition into the wilds of Central Park in New York City.
Jamie Whitacre is the Smithsonian database developer for the project.
Ellen Farr is the Smithsonian Botany Department computer specialist.
Rusty Russell, US Herbarium Manager, is the Smithsonian co-investigator for the project.
W. John Kress, PhD. is the Principal Investigator of the Leaf Project at the Smithsonian.
Ingrid Pol-Yin Lin is the Smithsonian photographer who images voucher specimens and leaves used in the project.
Norm Bourg has collected plants and worked on the development of early electronic field guide prototypes that eventually led to LeafSnap.
James Short is a long-term volunteer in the Smithsonian Botany Department. He assists with specimen and image data processing.
Linda Keenan writes Plant Profiles and has collected plants in the DC and Boston areas.
Leonel Velasquez interns for the Finding Species team on LeafSnap special expeditions.
Tanya Tarasova has researched flowering times, coordinated expeditions, and assisted with permits. She has provided administrative oversight.
Norm Bourg has collected plants and worked on the development of early electronic field guide prototypes that eventually led to LeafSnap.
Bejat McCracken is the lead Finding Species photographer for LeafSnap. She supervises the project, trains the botanical photographers, and processes photos.
Hugo Mogollon has supervised the Finding Species team, in the US and South America.
Roxana Bravo has refined details in the high-resolution photographic method, and has photographed plants.
Gorky F. Villa Muñoz is the lead Finding Species botanist for LeafSnap. He collects and photographs plants throughout the US and manages databases.
Christopher Lewis located and identified plants, while providing feedback on the botanical aspects of the high-resolution photographs.
Diego Acosta assisted with processing and editing photographs, and photographed plants on special expeditions.
Martin Bustamante has coordinated the Finding Species photographers and solved photographic challenges.
Neil Kaufman interns for Finding Species writing Plant Profiles and working with photographic databases.
Michelle Downey collected plants in the Southeastern US and processed photographs.
Gorky F. Villa Muñoz is the lead Finding Species botanist for LeafSnap. He collects and photographs plants throughout the US and manages databases.
Yuri Huta created Finding Species'' photographic method for the high-resolution photographs in LeafSnap, and has photographed plants.
Margot S. Bass coordinated the Finding Species LeafSnap US team, and conceived the standardized high-resolution plant photographs.
Michael Honsaker has provided technology support and maintained photographic metadata.
The Leafsnap team extends many thanks to the gardens, parks and arboreta which gave us the opportunities to photograph and gather data for the Leafsnap app.
Our sincere appreciation to the following individuals who have facilitated use of their garden, park or arboretum collections and supported the team in gathering data for Leafsnap.
Ellie Altman, Edward Sibley Barnard, Jane and George Bass, Scott Bell, Carole Bergmann, Todd Bolton, Norman Bourg, Ph.D., Matthew Brown, Andrew Bunting, Neil Calvanese, David Carr, Nancy Cowden, PhD., Charlie Davis, Ted Delaney, Michael S. Dosmann, Ph.D., Geoffrey Fenner, Doug Gill, Ph.D., Sarah Hill, Jack Kyte, Richard Lieberman, Cheryl A. Lindeman, Ed.D., Rhoda Maurer, Shawn McCracken, PhD, Phil Normandy, Janice Owens, Kathryn Reshetiloff, Kathryn Richardson, T'ai Roulston, and Kevin Tunison.
The addition of Canadian tree species of was made possible through the generosity of TD Friends of the Environment Foundation.
Contact us at [email protected] or follow @leafsnap on Twitter! View our Privacy Policy.