Image recognition tool added to FlorApp

Researchers from the Swiss Federal Institute for Forest, Snow and Landscape Research (WSL) in Birmensdorf in the canton of Zurich have developed the FlorID image recognition software for the FlorApp from Info Flora, the National Data and Information Center on the Swiss Flora. FlorID can recognize more than 3,000 species of plant with a high degree of reliability, as the WSL writes in a press release. “We have trained the computer with almost 1.5 million images and information on locations from the Info Flora data center”, comments macroecologist Philipp Brun, who programmed the FlorID tool, in the press release. For the training data, a WSL employee searched for and photographed around 260 rare species of flora.

FlorID is highly accurate. “In over 95 percent of cases, the correct species is among the first five suggestions, with the first suggestion being the correct one in about 85 percent of cases”, Brun explains. The fact that the app is also able to process information as to where the plants were found is a factor in the excellent hit rate. “This increases the accuracy of the results compared to other plant recognition apps”, Brun adds.

The new image recognition tool is not only intended to make it easier for users to identify plants. Rather, Brun expects that the expansion will also increase the quality and volume of data available to the Info Flora data center. WSL could use the data to improve the informative value of its biodiversity analyses. In addition, the FlorID concept could also be extended to help with the identification of other organisms. “We expect to be able to improve the data basis for various species groups with our tool. This should make the work around biodiversity surveys noticeably easier”, Brun concludes. ce/hs