SmartWoodID—an image collection of large end-grain surfaces to support wood identification systems

• DOI: 10.1093/database/baad034
• Publication Date: 2023-05-13T16:14:39Z
• Authors: Ruben De Blaere; Kévin Lievens; Dieter Van Hassel; Victor Deklerck; Tom De Mil; Wannes Hubau; Joris Van Acker; Nils Bourland; Jan Verwaeren; Jan Van den Bulcke; Hans Beeckman
• Keywords: Identification

Abstract Wood identification is a key step in the enforcement of laws and regulations aimed at combatting illegal timber trade. Robust wood tools, capable distinguishing large number timbers, depend on solid database reference material. Reference material for typically curated botanical collections dedicated to consisting samples secondary xylem lignified plants. Specimens from Tervuren Collection, one institutional around world, are used as source tree species data with potential application timber. Here, we present SmartWoodID, high-resolution optical scans end-grain surfaces enriched expert anatomical descriptions macroscopic features. These can serve annotated training develop interactive keys artificial intelligence computer vision–based identification. The first edition consists images 1190 taxa, focus Democratic Republic Congo least four different specimens per included. Database URL https://hdl.handle.net/20.500.12624/SmartWoodID_first_edition