Abstract
Applications for botanical identification from photographs are now available. Among them, Pl@ntNet was tested on two hundred photographs of leaves of twenty forest tree species. The results varied depending on the species, the number of photographs used for learning, and various parameters linked to the shots (the season, the number of leaves on the photograph, the way the leaves are presented, orthogonality of the shot). The results are analysed by group of species. The limitations and advantages of this application are discussed, and potential uses are presented.
Highlights:
• Automatic identification of tree species from photographs is now possible.
• The accuracy of identification is quite variable.
• It mainly varies according to species.
References
- Breiman, L. (2001). Random forests. Machine learning, 45(1), 5-32. doi:10.1023/A:1010933404324
- Dumé, G., Gauberville, C., Mansion, D., & Rameau, J.C. (2018). Flore forestière française. Guide écologique illustré. Tome 1 : Plaines et collines. Paris : Institut pour le développement forestier. 2e édition : 2460 p.
- Gaudin, S. (2013). Photographier la forêt, photographier en forêt : initiation à la prise de vue, méthode et guide pratique. Paris : Institut pour le développement forestier. 272 p.
- Gaudin, S., & Mouas, M. (2016). PhotoFor : une base de données photographiques dédiée à la forêt. Forêt-Entreprise, (228), 6-9.
- Goëau, H., Joly, A., Bonnet, P., Bakic, V., Barthélémy, D., Boujemaa, N., & Molino, J.F. (2013). The ImageCLEF 2013 Plant Identification Task. In: Proceedings of the 2nd ACM international workshop on Multimedia analysis for ecological data. 23-28. https://inria.hal.science/hal-00960929
- Horisberger, D. (2016). Détermination des chênes – Clé et utilisation pratique. Fiche technique. Éd. proQuercus. 10 p.
- Joly, A., Goëau, H., Bonnet, P., Bakić, V., Molino, J. F., Barthélémy, D., & Boujemaa, N. (2013). The imageclef plant identification task 2013. In: MAED: Multimedia Analysis for Ecological Data, Barcelone, Spain, 23-28. doi:10.1145/2509896.2509902
- Joly, A., Goëau, H., Bonnet, P., Bakić, V., Barbe, J., Selmi, S., ... & Barthélémy, D. (2014). Interactive plant identification based on social image data. Ecological Informatics, 23, 22-34. doi:10.1016/j.ecoinf.2013.07.006
- Joly, A., Bonnet, P., Goëau, H., Barbe, J., Selmi, S., Champ, J., ... & Barthélémy, D. (2016). A look inside the Pl@ntNet experience. Multimedia Systems, 22(6), 751-766. doi:10.1007/s00530-015-0462-9
- Lambinon, J., Delvosalle, L., Duvigneaud, J. et al. (2004). Nouvelle Flore de Belgique, du Grand Duché de Luxembourg, du Nord de la France et des Régions voisines (Ptéridophytes et Spermatophytes). Meise : Éditions du Patrimoine du Jardin botanique national de Belgique. 5e édition : 1167 p.
- Lang, V., & Šorgo, A. (2022). Added value of the pl@ntnet smartphone application for the motivation and performance of lower secondary school students in species identification. In: ICERI2022 Proceedings. 15th Annual International Conference of Education, Research and Innovation, 7-9 November, 2022, Seville, Spain, IATED, 4534-4540. doi:10.21125/iceri.2022.1091
- Rameau, J.C., Mansion, D., Dumé, G., & Gauberville, C. (2008). Flore forestière française. Guide écologique illustré. Tome 3 : région méditerranéenne. Paris : CNPF-IDF. 2426 p.
- Tison, J.M., & de Foucault, B. (2014). Flora gallica : flore de France. Éd. Biotope. 1196 p.

Views: 3052