Leaf recognition of woody species in Central Europe

• Published in: Biosystems engineering Vol. 115; no. 4; pp. 444 - 452
• Main Authors: Novotný, Petr, Suk, Tomáš
• Format: Journal Article
• Language: English
• Published: Kidlington Elsevier Ltd 01.08.2013; Elsevier
• Subjects: Agricultural machinery and engineering; Agronomy. Soil science and plant productions; algorithms; Biological and medical sciences; data collection; engineering; Fundamental and applied biological sciences. Psychology; Generalities. Biometrics, experimentation. Remote sensing; Internet; leaves; woody plants; Central European region; Central Europe; Europe; Bioengineering; Engineering; Vegetative apparatus; Agriculture; Plant leaf; Woody plant; Temperate zone; Species; Recognition
• ISSN: 1537-5110; 1537-5129
• DOI: 10.1016/j.biosystemseng.2013.04.007

A system for recognition of woody species in Central Europe according to the images of their leaves is described. Our own data set, which includes 151 species at this moment, with at least 50 leaves per species was used. After segmentation, the contour of the leaf was traced. Fourier descriptors normalised to translation, rotation, scaling and starting point of the boundary, were used. The size of the leaf, if known, was used as a separate feature. The nearest neighbour classifier was used. The algorithm is available through a web application. •A system for recognition of woody species in Central Europe is described.•Our own data set, with 151 species and at least 50 leaves per species is used.•After segmentation, the contour of the leaf can be traced.•Fourier descriptors normalised to TRS and starting point of the boundary used.•Nearest neighbour classifier is used.