A recent study from the Proceedings of the National Academy of Sciences discussed the potential of computers to assist in the classification of leaves, Brown University said.
It was proposed that a machine-programmed algorithm had the ability to distinguish between patterns of leaves at such a level of accuracy that leaves submitted to the program were identified with over 70 percent accuracy.
"Families and orders represent many thousands of species each, with incredible variation among the species, far beyond what botanists have been able to describe using the standard methods," Paul Wilf, a paleobotanist from Penn State University, said.
The program is able to discern very subtle differences in venation, making the sorting and classifying much easier and less involved for botanists.
"We can do things with computer vision that would be simply impossible if we were to rely on human annotations," Thomas Serre, a computer vision expert, said about the advances in the technology.
Wilf and Serre worked together on the leaf classification system following Serre's release of a system that monitored the behavior of mice. The data gleaned from the program represented both time saved and valuable information collected. It is hoped that the same will come out of this new classification of leaves.