Fusion system based on belief functions theory and approximated belief functions for tree species recognition

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.