Automatic ladybird beetle detection using deep-learning models.

Fast and accurate taxonomic identification of invasive trans-located ladybird beetle species is essential to prevent significant impacts on biological communities, ecosystem functions, and agricultural business economics. Therefore, in this work we propose a two-step automatic detector for ladybird...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Pablo Venegas, Francisco Calderon, Daniel Riofrío, Diego Benítez, Giovani Ramón, Diego Cisneros-Heredia, Miguel Coimbra, José Luis Rojo-Álvarez, Noel Pérez
Formato:	article
Lenguaje:	EN
Publicado:	Public Library of Science (PLoS) 2021
Materias:	Medicine R Science Q
Acceso en línea:	https://doaj.org/article/0500f7ca39854bf587c44aa27e8087a6
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:0500f7ca39854bf587c44aa27e8087a6
record_format	dspace
spelling	oai:doaj.org-article:0500f7ca39854bf587c44aa27e8087a62021-12-02T20:10:47ZAutomatic ladybird beetle detection using deep-learning models.1932-620310.1371/journal.pone.0253027https://doaj.org/article/0500f7ca39854bf587c44aa27e8087a62021-01-01T00:00:00Zhttps://doi.org/10.1371/journal.pone.0253027https://doaj.org/toc/1932-6203Fast and accurate taxonomic identification of invasive trans-located ladybird beetle species is essential to prevent significant impacts on biological communities, ecosystem functions, and agricultural business economics. Therefore, in this work we propose a two-step automatic detector for ladybird beetles in random environment images as the first stage towards an automated classification system. First, an image processing module composed of a saliency map representation, simple linear iterative clustering superpixels segmentation, and active contour methods allowed us to generate bounding boxes with possible ladybird beetles locations within an image. Subsequently, a deep convolutional neural network-based classifier selects only the bounding boxes with ladybird beetles as the final output. This method was validated on a 2, 300 ladybird beetle image data set from Ecuador and Colombia obtained from the iNaturalist project. The proposed approach achieved an accuracy score of 92% and an area under the receiver operating characteristic curve of 0.977 for the bounding box generation and classification tasks. These successful results enable the proposed detector as a valuable tool for helping specialists in the ladybird beetle detection problem.Pablo VenegasFrancisco CalderonDaniel RiofríoDiego BenítezGiovani RamónDiego Cisneros-HerediaMiguel CoimbraJosé Luis Rojo-ÁlvarezNoel PérezPublic Library of Science (PLoS)articleMedicineRScienceQENPLoS ONE, Vol 16, Iss 6, p e0253027 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Medicine R Science Q
spellingShingle	Medicine R Science Q Pablo Venegas Francisco Calderon Daniel Riofrío Diego Benítez Giovani Ramón Diego Cisneros-Heredia Miguel Coimbra José Luis Rojo-Álvarez Noel Pérez Automatic ladybird beetle detection using deep-learning models.
description	Fast and accurate taxonomic identification of invasive trans-located ladybird beetle species is essential to prevent significant impacts on biological communities, ecosystem functions, and agricultural business economics. Therefore, in this work we propose a two-step automatic detector for ladybird beetles in random environment images as the first stage towards an automated classification system. First, an image processing module composed of a saliency map representation, simple linear iterative clustering superpixels segmentation, and active contour methods allowed us to generate bounding boxes with possible ladybird beetles locations within an image. Subsequently, a deep convolutional neural network-based classifier selects only the bounding boxes with ladybird beetles as the final output. This method was validated on a 2, 300 ladybird beetle image data set from Ecuador and Colombia obtained from the iNaturalist project. The proposed approach achieved an accuracy score of 92% and an area under the receiver operating characteristic curve of 0.977 for the bounding box generation and classification tasks. These successful results enable the proposed detector as a valuable tool for helping specialists in the ladybird beetle detection problem.
format	article
author	Pablo Venegas Francisco Calderon Daniel Riofrío Diego Benítez Giovani Ramón Diego Cisneros-Heredia Miguel Coimbra José Luis Rojo-Álvarez Noel Pérez
author_facet	Pablo Venegas Francisco Calderon Daniel Riofrío Diego Benítez Giovani Ramón Diego Cisneros-Heredia Miguel Coimbra José Luis Rojo-Álvarez Noel Pérez
author_sort	Pablo Venegas
title	Automatic ladybird beetle detection using deep-learning models.
title_short	Automatic ladybird beetle detection using deep-learning models.
title_full	Automatic ladybird beetle detection using deep-learning models.
title_fullStr	Automatic ladybird beetle detection using deep-learning models.
title_full_unstemmed	Automatic ladybird beetle detection using deep-learning models.
title_sort	automatic ladybird beetle detection using deep-learning models.
publisher	Public Library of Science (PLoS)
publishDate	2021
url	https://doaj.org/article/0500f7ca39854bf587c44aa27e8087a6
work_keys_str_mv	AT pablovenegas automaticladybirdbeetledetectionusingdeeplearningmodels AT franciscocalderon automaticladybirdbeetledetectionusingdeeplearningmodels AT danielriofrio automaticladybirdbeetledetectionusingdeeplearningmodels AT diegobenitez automaticladybirdbeetledetectionusingdeeplearningmodels AT giovaniramon automaticladybirdbeetledetectionusingdeeplearningmodels AT diegocisnerosheredia automaticladybirdbeetledetectionusingdeeplearningmodels AT miguelcoimbra automaticladybirdbeetledetectionusingdeeplearningmodels AT joseluisrojoalvarez automaticladybirdbeetledetectionusingdeeplearningmodels AT noelperez automaticladybirdbeetledetectionusingdeeplearningmodels
_version_	1718374924634030080

Automatic ladybird beetle detection using deep-learning models.

Ejemplares similares