Bark and Leaf Fusion Systems to Improve Automatic Tree Species Recognition

Abstract : For everyone, the identification of tree is a difficult task. The main organ of the plant used generally to identify a tree is the leaf. However, due to the large variability of the shapes of leaves, it is difficult to obtain good recognition results. Moreover, sometimes the bark is a very distinctive feature and we think it may be possible to improve the recognition rate by considering it. The main purpose of this article is to investigate how we can combine the features extracted respectively from the leaf and the bark images to recognize the tree the photos come from. An important point is the consideration of the confusion matrix that can be constructed between several species, when the form of a leaf or the shape of a bark is common to a number of tree species. So, we present various strategies of fusion including belief functions and compare them on a public database of 72 species of trees and shrubs, which can be find in metropolitan France.
Type de document :
Article dans une revue
Ecological Informatics, Elsevier, 2018, 〈10.1016/j.ecoinf.2018.05.007〉
Liste complète des métadonnées
Contributeur : Sarah Bertrand <>
Soumis le : vendredi 8 juin 2018 - 14:43:27
Dernière modification le : jeudi 29 novembre 2018 - 01:21:43



Sarah Bertrand, Rihab Ben Ameur, Guillaume Cerutti, Didier Coquin, Lionel Valet, et al.. Bark and Leaf Fusion Systems to Improve Automatic Tree Species Recognition. Ecological Informatics, Elsevier, 2018, 〈10.1016/j.ecoinf.2018.05.007〉. 〈hal-01811039〉



Consultations de la notice