A reference process for automating bee species identification based on wing images and digital image processing

Fabiana SANTANA, Anna Costa, Flavio Truzzi, Felipe Silva, Sheila Santos, Tiago Francoy, Antonio Saraiva

Research output: Contribution to journalArticle

9 Citations (Scopus)

Abstract

Pollinators play a key role in biodiversity conservation, since they provide vital services to both natural ecosystems and agriculture. In particular, bees are excellent pollinators; therefore, their mapping, classification, and preservation help to promote biodiversity conservation. However, these tasks are difficult and time consuming since there is a lack of classification keys, sampling efforts and trained taxonomists. The development of tools for automating and assisting the identification of bee species represents an important contribution to biodiversity conservation. Several studies have shown that features extracted from patterns of bee wings are good discriminatory elements to differentiate among species, and some have devoted efforts to automate this process. However, the automated identification of bee species is a particularly hard problem, because (i) individuals of a given species may vary hugely in morphology, and (ii) closely related species may be extremely similar to one another. This paper proposes a reference process for bee classification based on wing images to provide a complete understanding of the problem from the experts' point of view, and a foundation to software systems development and integration using Internet services. The results can be extended to other species identification and taxonomic classification, as long as similar criteria are applicable. The reference process may also be helpful for beginners in this research field, as they can use the process and the experiments presented here as a guide to this complex activity.
Original languageEnglish
Pages (from-to)248-260
Number of pages13
JournalEcological Informatics
Volume24
DOIs
Publication statusPublished - 2014
Externally publishedYes

Fingerprint

Digital Image Processing
digital images
digital image
image processing
bee
Apoidea
Biodiversity
Image processing
image analysis
Conservation
taxonomy
biodiversity
pollinators
pollinator
Ecosystems
Agriculture
Computer systems
System Integration
Internet
System Development

Cite this

SANTANA, Fabiana ; Costa, Anna ; Truzzi, Flavio ; Silva, Felipe ; Santos, Sheila ; Francoy, Tiago ; Saraiva, Antonio. / A reference process for automating bee species identification based on wing images and digital image processing. In: Ecological Informatics. 2014 ; Vol. 24. pp. 248-260.
@article{66b49fef260c41808556a25859616605,
title = "A reference process for automating bee species identification based on wing images and digital image processing",
abstract = "Pollinators play a key role in biodiversity conservation, since they provide vital services to both natural ecosystems and agriculture. In particular, bees are excellent pollinators; therefore, their mapping, classification, and preservation help to promote biodiversity conservation. However, these tasks are difficult and time consuming since there is a lack of classification keys, sampling efforts and trained taxonomists. The development of tools for automating and assisting the identification of bee species represents an important contribution to biodiversity conservation. Several studies have shown that features extracted from patterns of bee wings are good discriminatory elements to differentiate among species, and some have devoted efforts to automate this process. However, the automated identification of bee species is a particularly hard problem, because (i) individuals of a given species may vary hugely in morphology, and (ii) closely related species may be extremely similar to one another. This paper proposes a reference process for bee classification based on wing images to provide a complete understanding of the problem from the experts' point of view, and a foundation to software systems development and integration using Internet services. The results can be extended to other species identification and taxonomic classification, as long as similar criteria are applicable. The reference process may also be helpful for beginners in this research field, as they can use the process and the experiments presented here as a guide to this complex activity.",
keywords = "machine-learning, digital-image-processing, taxonomic-classification",
author = "Fabiana SANTANA and Anna Costa and Flavio Truzzi and Felipe Silva and Sheila Santos and Tiago Francoy and Antonio Saraiva",
year = "2014",
doi = "10.1016/j.ecoinf.2013.12.001",
language = "English",
volume = "24",
pages = "248--260",
journal = "Ecological Informatics",
issn = "1574-9541",
publisher = "Elsevier",

}

A reference process for automating bee species identification based on wing images and digital image processing. / SANTANA, Fabiana; Costa, Anna; Truzzi, Flavio; Silva, Felipe; Santos, Sheila; Francoy, Tiago; Saraiva, Antonio.

In: Ecological Informatics, Vol. 24, 2014, p. 248-260.

Research output: Contribution to journalArticle

TY - JOUR

T1 - A reference process for automating bee species identification based on wing images and digital image processing

AU - SANTANA, Fabiana

AU - Costa, Anna

AU - Truzzi, Flavio

AU - Silva, Felipe

AU - Santos, Sheila

AU - Francoy, Tiago

AU - Saraiva, Antonio

PY - 2014

Y1 - 2014

N2 - Pollinators play a key role in biodiversity conservation, since they provide vital services to both natural ecosystems and agriculture. In particular, bees are excellent pollinators; therefore, their mapping, classification, and preservation help to promote biodiversity conservation. However, these tasks are difficult and time consuming since there is a lack of classification keys, sampling efforts and trained taxonomists. The development of tools for automating and assisting the identification of bee species represents an important contribution to biodiversity conservation. Several studies have shown that features extracted from patterns of bee wings are good discriminatory elements to differentiate among species, and some have devoted efforts to automate this process. However, the automated identification of bee species is a particularly hard problem, because (i) individuals of a given species may vary hugely in morphology, and (ii) closely related species may be extremely similar to one another. This paper proposes a reference process for bee classification based on wing images to provide a complete understanding of the problem from the experts' point of view, and a foundation to software systems development and integration using Internet services. The results can be extended to other species identification and taxonomic classification, as long as similar criteria are applicable. The reference process may also be helpful for beginners in this research field, as they can use the process and the experiments presented here as a guide to this complex activity.

AB - Pollinators play a key role in biodiversity conservation, since they provide vital services to both natural ecosystems and agriculture. In particular, bees are excellent pollinators; therefore, their mapping, classification, and preservation help to promote biodiversity conservation. However, these tasks are difficult and time consuming since there is a lack of classification keys, sampling efforts and trained taxonomists. The development of tools for automating and assisting the identification of bee species represents an important contribution to biodiversity conservation. Several studies have shown that features extracted from patterns of bee wings are good discriminatory elements to differentiate among species, and some have devoted efforts to automate this process. However, the automated identification of bee species is a particularly hard problem, because (i) individuals of a given species may vary hugely in morphology, and (ii) closely related species may be extremely similar to one another. This paper proposes a reference process for bee classification based on wing images to provide a complete understanding of the problem from the experts' point of view, and a foundation to software systems development and integration using Internet services. The results can be extended to other species identification and taxonomic classification, as long as similar criteria are applicable. The reference process may also be helpful for beginners in this research field, as they can use the process and the experiments presented here as a guide to this complex activity.

KW - machine-learning

KW - digital-image-processing

KW - taxonomic-classification

UR - https://www.scopus.com/record/display.uri?eid=2-s2.0-85027948788&origin=resultslist&sort=plf-f&src=s&nlo=&nlr=&nls=&sid=78b82584e071103983fb2de16ddfc4dc&sot=a&sdt=cl&cluster=scopubyr%2c%222014%22%2ct&sl=22&s=SOURCE-ID+%283100147401%29&relpos=13&citeCnt=5&searchTerm=

U2 - 10.1016/j.ecoinf.2013.12.001

DO - 10.1016/j.ecoinf.2013.12.001

M3 - Article

VL - 24

SP - 248

EP - 260

JO - Ecological Informatics

JF - Ecological Informatics

SN - 1574-9541

ER -