INVESTIGADORES
DELRIEUX Claudio Augusto
artículos
Título:
Wild Cetacean Identification using Image Metadata
Autor/es:
DEBORA POLLICELLI; CLAUDIO DELRIEUX; MARIANO COSCARELLA
Revista:
JOURNAL OF COMPUTER SCIENCE AND TECHNOLOGY
Editorial:
SCIENCE PRESS
Referencias:
Lugar: Marrickville NSW; Año: 2017
ISSN:
1000-9000
Resumen:
Identification of individuals inmarine species, especially in Cetacea, isa critical task in several biological and ecological endeavours. Most of the times this is performed through human-assisted matchingwithin a set of pictures taken in different campaigns during several years and spread around wide geographical regions. This requires that the sci- entists perform laborious tasks in searching through archives of images, demanding a significant cognitive burden which may be prone to intra-and interobserver operationalerrors. On the other hand, additional avail- able information, in particular the metadata associatedto every image,is not fully taken advantage of. The present work presents the result ofapplying machine learning techniques over the metadataof archives ofimages as an aid in the process of manual identification. The method was tested ona database containing several pictures of230 different Com- merson?s dolphins (Cephalorhynchus commersoni) taken over a span ofseven years. A supervisedclassifier trained with identifications made by the researchers was able to identify correctly above 90%of the individ- uals on the test set using only the metadata present in the image files.This reduces significantly the number of images to be manually com- pared, and therefore the time and errors associated with the assisted identification process.