Wild Cetacean Identification using Image Metadata

Identification of individuals in marine species, especially in Cetacea, is a critical task in several biological and ecological endeavours. Most of the times this is performed through human-assisted matching within a set of pictures taken in different campaigns during several years and spread around...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Pollicelli, Débora, Coscarella, Mariano, Delrieux, Claudio
Formato: Objeto de conferencia
Lenguaje:Inglés
Publicado: 2016
Materias:
Ciencias Informáticas
machine learning
photo-identification
Acceso en línea:http://sedici.unlp.edu.ar/handle/10915/56759
Aporte de:
SEDICI (UNLP) de Universidad Nacional de La Plata
id I19-R120-10915-56759
record_format dspace
institution Universidad Nacional de La Plata
institution_str I-19
repository_str R-120
collection SEDICI (UNLP)
language Inglés
topic Ciencias Informáticas
machine learning
photo-identification
spellingShingle Ciencias Informáticas
machine learning
photo-identification
Pollicelli, Débora
Coscarella, Mariano
Delrieux, Claudio
Wild Cetacean Identification using Image Metadata
topic_facet Ciencias Informáticas
machine learning
photo-identification
description Identification of individuals in marine species, especially in Cetacea, is a critical task in several biological and ecological endeavours. Most of the times this is performed through human-assisted matching within a set of pictures taken in different campaigns during several years and spread around wide geographical regions. This requires that the scientists perform laborious tasks in searching through archives of images, demanding a significant cognitive burden which may be prone to intra and inter observer operational errors. On the other hand, additional available information, in particular the metadata associated to every image, is not fully taken advantage of. The present work presents the result of applying machine learning techniques over the metadata of archives of images as an aid in the process of manual identification. The method was tested on a database containing several pictures of 230 different Commerson’s dolp hins (Cephalorhynchus commersoni) taken over a span of seven years. A supervised classifier trained with identifications made by the researchers was able to identify correctly above 90% of the individuals on the test set using only the metadata present in the image files. This reduces significantly the number of images to be manually compared, and therefore the time and errors associated with the assisted identification process.
format Objeto de conferencia
Objeto de conferencia
author Pollicelli, Débora
Coscarella, Mariano
Delrieux, Claudio
author_facet Pollicelli, Débora
Coscarella, Mariano
Delrieux, Claudio
author_sort Pollicelli, Débora
title Wild Cetacean Identification using Image Metadata
title_short Wild Cetacean Identification using Image Metadata
title_full Wild Cetacean Identification using Image Metadata
title_fullStr Wild Cetacean Identification using Image Metadata
title_full_unstemmed Wild Cetacean Identification using Image Metadata
title_sort wild cetacean identification using image metadata
publishDate 2016
url http://sedici.unlp.edu.ar/handle/10915/56759
work_keys_str_mv AT pollicellidebora wildcetaceanidentificationusingimagemetadata
AT coscarellamariano wildcetaceanidentificationusingimagemetadata
AT delrieuxclaudio wildcetaceanidentificationusingimagemetadata
bdutipo_str Repositorios
_version_ 1764820477564420097

Ejemplares similares