Classification of Pollen Apertures Using Bag of Words

Gildardo Lozano-Vega (1, 2) , Yannick Benezeth (1) , Franck S. Marzani (1) , Frank Boochs (2)

1 Le2i - Laboratoire Electronique, Informatique et Image [UMR6306]
2 i3mainz - Institut für Raumbezogene Informations- und Messtechnik

The taxonomical recognition of microscopic biological parti- cles such as pollen and spores is relevant for medical and aerobiological applications. Focusing on an accurate and automatic vision-based pollen recognition system, we propose a method for classification of pollen aper- tures based on bag-of-words strategy, with the ability of learning new types from different taxa without the need of new algorithms. Results demonstrate suitable performance and ability to add new taxa.

Domaines: Informatique [cs]; Traitement des images [eess.IV]

Gildardo Lozano-Vega, Yannick Benezeth, Franck S. Marzani, Frank Boochs. Classification of Pollen Apertures Using Bag of Words. International Conference on Image Analysis and Processing (ICIAP), Sep 2013, Italy. ⟨10.1007/978-3-642-41184-7⟩. ⟨hal-00857927⟩