LeafMachine2 is now available and has improved upon the original LeafMachine concept in every way. Please see leafmachine.org or github.com/Gene-Weaver/LeafMachine2 for updates. We recommend using LeafMachine2 going forward and will no longer support the original Matlab version of LeafMachine.
LeafMachine is a GUI that autonomously extracts leaf trait data from herbarium vouchers using CNNs, SVMs, and CV algorithms. There are two GUIs: manual version for fine-scale analyses, batch version for local files or from a list of URLs.
Branch V.2.0 is the version described in the publication.
Branch V.2.1 contains improvements, not stable or recommended for use yet.
Weaver, W. N., J. Ng, and R. G. Laport. 2020. LeafMachine: Using machine learning to automate leaf trait extraction from digitized herbarium specimens. Applications in Plant Sciences 8(6): e11367. https://doi.org/10.1002/aps3.11367
Supported by NSF 1930030, NSF‐EF 1550813, Microsoft AI for Earth