Fusion system based on belief functions theory and approximated belief functions for tree species recognition
Rihab Ben Ameur, Lionel Valet, Didier Coquin · 2016
In this paper, an information fusion system for tree species recognition through leaves is proposed. This approach consists in training sub-classifiers (Random forests) with attributes extracted from leaf photos. The database is incomplete, partial and some data is conflicting. A hierarchical fusion system based on Belief functions theory allows the fusion of data provided by different sub-classifiers. Different procedures for reducing computational complexity are tested.