Are species identification tools biodiversity-friendly ?

Müller, Henning (University of Applied Sciences and Arts Western Switzerland (HES-SO Valais-Wallis)) ; Joly, Alexis (INRIA, LIRMM, France) ; Goëau, Hervé (INRIA, LIRMM, France) ; Bonnet, Pierre (CIRAD, AMAP, France) ; Spampinato, Concetto (University of Catania, Italy) ; Glotin, Hervé (IUF & University of Toulon, France) ; Rauber, Andreas (Vienna University of Technology, Austria) ; Vellinga, Willem-Pier (Xeno-canto fundation, Amsterdam, Holland) ; Fisher, Robert (Edinburgh University, UK)

This paper discusses the results of the LifeCLEF 2014 multimedia identification challenges with regards to the requirements of real-world ecological surveillance systems. In particular, we study the identification performances of the evaluated systems as a function of the ordinariness or rarity of the species in the dataset. This allows us to assess the ability of the underlying methods to be robust to heavily tailed distributions such as the ones encountered in real-world collections of life observations. Results show that all methods are more or less affected by the long-tail curse but that the best methods making use of classifiers with good discrimi- nation capacities do resist the phenomenon pretty well.


Mots-clés:
Type de conférence:
full paper
Faculté:
Economie et Services
Ecole:
HEG - Valais
Institut:
Institut Informatique de gestion
Classification:
Informatique
Adresse bibliogr.:
Orlando, USA, 3-7 November 2014
Date:
Orlando, USA
3-7 November 2014
2014
Pagination:
6 p.
Publié dans
Proceedings of the 3rd ACM International Workshop on Multimedia Analysis for Ecological Data (MAED) 2014
DOI:
ISBN:
978-1-4503-3123-4
Le document apparaît dans:

Note: The status of this file is: restricted


 Notice créée le 2015-11-15, modifiée le 2018-12-07

Fichiers:
Télécharger le document
PDF

Évaluer ce document:

Rate this document:
1
2
3
 
(Pas encore évalué)