Novel automatic scorpion-detection and -recognition system based on machine-learning techniques

Autores
Giambelluca, Francisco Luis; Osio, Jorge Rafael; Giambelluca, Luis A.; Cappelletti, Marcelo
Año de publicación
2021
Idioma
inglés
Tipo de recurso
artículo
Estado
versión publicada
Descripción
All species of scorpions can inject venom, some of them even with the possibility of killing a human. Therefore, early detection and identification are essential to minimize scorpion stings. In this paper, we propose a novel automatic system for the detection and recognition of scorpions using computer vision and machine learning (ML) approaches. Two complementary image-processing techniques were used for the proposed detection method to accurately and reliably detect the presence of scorpions. The first is based on the fluorescent characteristics of scorpions when exposed to ultraviolet light, and the second on the shape features of the scorpions. Also, three models based on ML algorithms for the image recognition and classification of scorpions are compared. In particular, the three species of scorpions found in La Plata city (Argentina): Bothriurus bonariensis (of no sanitary importance), Tityus trivittatus, and Tityus confluence (both of sanitary importance) have been researched using a local binary-pattern histogram algorithm and deep neural networks with transfer learning (DNNs with TL) and data augmentation (DNNs with TL and DA) approaches. A confusion matrix and a receiver operating characteristic curve were used to evaluate the quality of these models. The results obtained show that the model of DNN with TL and DA is the most efficient at simultaneously differentiating between Tityus and Bothriurus (for health security) and between T. trivittatus and T. confluence (for biological research purposes).
Fil: Giambelluca, Francisco Luis. Universidad Nacional de La Plata. Facultad de Ingeniería. Instituto de Investigaciones en Electrónica, Control y Procesamiento de Señales; Argentina.
Fil: Giambelluca, Francisco Luis. Consejo Nacional de Investigaciones Científicas y Técnicas. Facultad de Ingeniería. Instituto de Investigaciones en Electrónica, Control y Procesamiento de Señales; Argentina.
Fil: Cappelletti, Marcelo. Universidad Nacional de La Plata. Facultad de Ingeniería. Instituto de Investigaciones en Electrónica, Control y Procesamiento de Señales; Argentina.
Fil: Cappelletti, Marcelo. Consejo Nacional de Investigaciones Científicas y Técnicas. Facultad de Ingeniería. Instituto de Investigaciones en Electrónica, Control y Procesamiento de Señales; Argentina.
Fil: Cappelletti, Marcelo. Universidad Nacional Arturo Jauretche. Programa Tecnologías de la información y la comunicación (TICs) en aplicaciones de interés social; Argentina.
Fil: Cappelletti, Marcelo. Consejo Nacional de Investigaciones Científicas y Técnicas. Facultad de Ingeniería; Argentina.
Fil: Osio, Jorge Rafael. Universidad Nacional de La Plata. Facultad de Ingeniería. Instituto de Investigaciones en Electrónica, Control y Procesamiento de Señales; Argentina.
Fil: Osio, Jorge Rafael. Consejo Nacional de Investigaciones Científicas y Técnicas. Facultad de Ingeniería. Instituto de Investigaciones en Electrónica, Control y Procesamiento de Señales; Argentina.
Fil: Osio, Jorge Rafael. Universidad Nacional Arturo Jauretche. Programa Tecnologías de la información y la comunicación (TICs) en aplicaciones de interés social; Argentina.
Fil: Giambelluca, Luis. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro de Estudios Parasitológicos y de Vectores; Argentina.
Fil: Giambelluca, Luis. Universidad Nacional de La Plata. Centro de Estudios Parasitológicos y de Vectores; Argentina.
Fil: Giambelluca, Luis. Comisión de Investigación Científica de la Provincia de Buenos Aires. Centro de Estudios Parasitológicos y de Vectores; Argentina.
Materia
Data augmentation
Local binary patter
Machine learning
Scorpion image classification
Transfer learning
Nivel de accesibilidad
acceso abierto
Condiciones de uso
info:ar-repo/semantics/accesoabierto
Repositorio
Repositorio Institucional Digital de Acceso Abierto
Institución
Universidad Nacional Arturo Jauretche
OAI Identificador
oai:rid.unaj.edu.ar:123456789/3640

id RIDUNAJ_4450d6a3593e7cdace40194fe9153cdc
oai_identifier_str oai:rid.unaj.edu.ar:123456789/3640
network_acronym_str RIDUNAJ
repository_id_str
network_name_str Repositorio Institucional Digital de Acceso Abierto
spelling Novel automatic scorpion-detection and -recognition system based on machine-learning techniquesGiambelluca, Francisco LuisOsio, Jorge RafaelGiambelluca, Luis A.Cappelletti, MarceloData augmentationLocal binary patterMachine learningScorpion image classificationTransfer learningAll species of scorpions can inject venom, some of them even with the possibility of killing a human. Therefore, early detection and identification are essential to minimize scorpion stings. In this paper, we propose a novel automatic system for the detection and recognition of scorpions using computer vision and machine learning (ML) approaches. Two complementary image-processing techniques were used for the proposed detection method to accurately and reliably detect the presence of scorpions. The first is based on the fluorescent characteristics of scorpions when exposed to ultraviolet light, and the second on the shape features of the scorpions. Also, three models based on ML algorithms for the image recognition and classification of scorpions are compared. In particular, the three species of scorpions found in La Plata city (Argentina): Bothriurus bonariensis (of no sanitary importance), Tityus trivittatus, and Tityus confluence (both of sanitary importance) have been researched using a local binary-pattern histogram algorithm and deep neural networks with transfer learning (DNNs with TL) and data augmentation (DNNs with TL and DA) approaches. A confusion matrix and a receiver operating characteristic curve were used to evaluate the quality of these models. The results obtained show that the model of DNN with TL and DA is the most efficient at simultaneously differentiating between Tityus and Bothriurus (for health security) and between T. trivittatus and T. confluence (for biological research purposes).Fil: Giambelluca, Francisco Luis. Universidad Nacional de La Plata. Facultad de Ingeniería. Instituto de Investigaciones en Electrónica, Control y Procesamiento de Señales; Argentina.Fil: Giambelluca, Francisco Luis. Consejo Nacional de Investigaciones Científicas y Técnicas. Facultad de Ingeniería. Instituto de Investigaciones en Electrónica, Control y Procesamiento de Señales; Argentina.Fil: Cappelletti, Marcelo. Universidad Nacional de La Plata. Facultad de Ingeniería. Instituto de Investigaciones en Electrónica, Control y Procesamiento de Señales; Argentina.Fil: Cappelletti, Marcelo. Consejo Nacional de Investigaciones Científicas y Técnicas. Facultad de Ingeniería. Instituto de Investigaciones en Electrónica, Control y Procesamiento de Señales; Argentina.Fil: Cappelletti, Marcelo. Universidad Nacional Arturo Jauretche. Programa Tecnologías de la información y la comunicación (TICs) en aplicaciones de interés social; Argentina.Fil: Cappelletti, Marcelo. Consejo Nacional de Investigaciones Científicas y Técnicas. Facultad de Ingeniería; Argentina.Fil: Osio, Jorge Rafael. Universidad Nacional de La Plata. Facultad de Ingeniería. Instituto de Investigaciones en Electrónica, Control y Procesamiento de Señales; Argentina.Fil: Osio, Jorge Rafael. Consejo Nacional de Investigaciones Científicas y Técnicas. Facultad de Ingeniería. Instituto de Investigaciones en Electrónica, Control y Procesamiento de Señales; Argentina.Fil: Osio, Jorge Rafael. Universidad Nacional Arturo Jauretche. Programa Tecnologías de la información y la comunicación (TICs) en aplicaciones de interés social; Argentina.Fil: Giambelluca, Luis. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro de Estudios Parasitológicos y de Vectores; Argentina.Fil: Giambelluca, Luis. Universidad Nacional de La Plata. Centro de Estudios Parasitológicos y de Vectores; Argentina.Fil: Giambelluca, Luis. Comisión de Investigación Científica de la Provincia de Buenos Aires. Centro de Estudios Parasitológicos y de Vectores; Argentina.2021-02-26info:eu-repo/semantics/articleinfo:eu-repo/semantics/publishedVersionhttp://purl.org/coar/resource_type/c_6501info:ar-repo/semantics/articuloapplication/pdfhttps://rid.unaj.edu.ar/handle/123456789/3640engMachine Learning: Science and Technology, 2(2)info:eu-repo/semantics/altIdentifier/doi/10.1088/2632-2153/abd51dinfo:eu-repo/semantics/altIdentifier/eissn/2632-2153info:eu-repo/semantics/altIdentifier/url/doi.org/10.1088/2632-2153/abd51dinfo:eu-repo/semantics/openAccessinfo:ar-repo/semantics/accesoabiertohttps://creativecommons.org/licenses/by/4.0/reponame:Repositorio Institucional Digital de Acceso Abiertoinstname:Universidad Nacional Arturo Jauretche2026-10-01T12:51:57Zoai:rid.unaj.edu.ar:123456789/3640instacron:UNAJInstitucionalhttps://rid.unaj.edu.ar/homeUniversidad públicahttps://www.unaj.edu.ar/https://rid.unaj.edu.ar/server/oai/snrdrepositorio@unaj.edu.arArgentinaopendoar:2026-10-01 12:51:57.621Repositorio Institucional Digital de Acceso Abierto - Universidad Nacional Arturo Jauretchefalse
dc.title.none.fl_str_mv Novel automatic scorpion-detection and -recognition system based on machine-learning techniques
title Novel automatic scorpion-detection and -recognition system based on machine-learning techniques
spellingShingle Novel automatic scorpion-detection and -recognition system based on machine-learning techniques
Giambelluca, Francisco Luis
Data augmentation
Local binary patter
Machine learning
Scorpion image classification
Transfer learning
title_short Novel automatic scorpion-detection and -recognition system based on machine-learning techniques
title_full Novel automatic scorpion-detection and -recognition system based on machine-learning techniques
title_fullStr Novel automatic scorpion-detection and -recognition system based on machine-learning techniques
title_full_unstemmed Novel automatic scorpion-detection and -recognition system based on machine-learning techniques
title_sort Novel automatic scorpion-detection and -recognition system based on machine-learning techniques
dc.creator.none.fl_str_mv Giambelluca, Francisco Luis
Osio, Jorge Rafael
Giambelluca, Luis A.
Cappelletti, Marcelo
author Giambelluca, Francisco Luis
author_facet Giambelluca, Francisco Luis
Osio, Jorge Rafael
Giambelluca, Luis A.
Cappelletti, Marcelo
author_role author
author2 Osio, Jorge Rafael
Giambelluca, Luis A.
Cappelletti, Marcelo
author2_role author
author
author
dc.subject.none.fl_str_mv Data augmentation
Local binary patter
Machine learning
Scorpion image classification
Transfer learning
topic Data augmentation
Local binary patter
Machine learning
Scorpion image classification
Transfer learning
dc.description.none.fl_txt_mv All species of scorpions can inject venom, some of them even with the possibility of killing a human. Therefore, early detection and identification are essential to minimize scorpion stings. In this paper, we propose a novel automatic system for the detection and recognition of scorpions using computer vision and machine learning (ML) approaches. Two complementary image-processing techniques were used for the proposed detection method to accurately and reliably detect the presence of scorpions. The first is based on the fluorescent characteristics of scorpions when exposed to ultraviolet light, and the second on the shape features of the scorpions. Also, three models based on ML algorithms for the image recognition and classification of scorpions are compared. In particular, the three species of scorpions found in La Plata city (Argentina): Bothriurus bonariensis (of no sanitary importance), Tityus trivittatus, and Tityus confluence (both of sanitary importance) have been researched using a local binary-pattern histogram algorithm and deep neural networks with transfer learning (DNNs with TL) and data augmentation (DNNs with TL and DA) approaches. A confusion matrix and a receiver operating characteristic curve were used to evaluate the quality of these models. The results obtained show that the model of DNN with TL and DA is the most efficient at simultaneously differentiating between Tityus and Bothriurus (for health security) and between T. trivittatus and T. confluence (for biological research purposes).
Fil: Giambelluca, Francisco Luis. Universidad Nacional de La Plata. Facultad de Ingeniería. Instituto de Investigaciones en Electrónica, Control y Procesamiento de Señales; Argentina.
Fil: Giambelluca, Francisco Luis. Consejo Nacional de Investigaciones Científicas y Técnicas. Facultad de Ingeniería. Instituto de Investigaciones en Electrónica, Control y Procesamiento de Señales; Argentina.
Fil: Cappelletti, Marcelo. Universidad Nacional de La Plata. Facultad de Ingeniería. Instituto de Investigaciones en Electrónica, Control y Procesamiento de Señales; Argentina.
Fil: Cappelletti, Marcelo. Consejo Nacional de Investigaciones Científicas y Técnicas. Facultad de Ingeniería. Instituto de Investigaciones en Electrónica, Control y Procesamiento de Señales; Argentina.
Fil: Cappelletti, Marcelo. Universidad Nacional Arturo Jauretche. Programa Tecnologías de la información y la comunicación (TICs) en aplicaciones de interés social; Argentina.
Fil: Cappelletti, Marcelo. Consejo Nacional de Investigaciones Científicas y Técnicas. Facultad de Ingeniería; Argentina.
Fil: Osio, Jorge Rafael. Universidad Nacional de La Plata. Facultad de Ingeniería. Instituto de Investigaciones en Electrónica, Control y Procesamiento de Señales; Argentina.
Fil: Osio, Jorge Rafael. Consejo Nacional de Investigaciones Científicas y Técnicas. Facultad de Ingeniería. Instituto de Investigaciones en Electrónica, Control y Procesamiento de Señales; Argentina.
Fil: Osio, Jorge Rafael. Universidad Nacional Arturo Jauretche. Programa Tecnologías de la información y la comunicación (TICs) en aplicaciones de interés social; Argentina.
Fil: Giambelluca, Luis. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro de Estudios Parasitológicos y de Vectores; Argentina.
Fil: Giambelluca, Luis. Universidad Nacional de La Plata. Centro de Estudios Parasitológicos y de Vectores; Argentina.
Fil: Giambelluca, Luis. Comisión de Investigación Científica de la Provincia de Buenos Aires. Centro de Estudios Parasitológicos y de Vectores; Argentina.
description All species of scorpions can inject venom, some of them even with the possibility of killing a human. Therefore, early detection and identification are essential to minimize scorpion stings. In this paper, we propose a novel automatic system for the detection and recognition of scorpions using computer vision and machine learning (ML) approaches. Two complementary image-processing techniques were used for the proposed detection method to accurately and reliably detect the presence of scorpions. The first is based on the fluorescent characteristics of scorpions when exposed to ultraviolet light, and the second on the shape features of the scorpions. Also, three models based on ML algorithms for the image recognition and classification of scorpions are compared. In particular, the three species of scorpions found in La Plata city (Argentina): Bothriurus bonariensis (of no sanitary importance), Tityus trivittatus, and Tityus confluence (both of sanitary importance) have been researched using a local binary-pattern histogram algorithm and deep neural networks with transfer learning (DNNs with TL) and data augmentation (DNNs with TL and DA) approaches. A confusion matrix and a receiver operating characteristic curve were used to evaluate the quality of these models. The results obtained show that the model of DNN with TL and DA is the most efficient at simultaneously differentiating between Tityus and Bothriurus (for health security) and between T. trivittatus and T. confluence (for biological research purposes).
publishDate 2021
dc.date.none.fl_str_mv 2021-02-26
dc.type.none.fl_str_mv info:eu-repo/semantics/article
info:eu-repo/semantics/publishedVersion
http://purl.org/coar/resource_type/c_6501
info:ar-repo/semantics/articulo
format article
status_str publishedVersion
dc.identifier.none.fl_str_mv https://rid.unaj.edu.ar/handle/123456789/3640
url https://rid.unaj.edu.ar/handle/123456789/3640
dc.language.none.fl_str_mv eng
language eng
dc.relation.none.fl_str_mv Machine Learning: Science and Technology, 2(2)
info:eu-repo/semantics/altIdentifier/doi/10.1088/2632-2153/abd51d
info:eu-repo/semantics/altIdentifier/eissn/2632-2153
info:eu-repo/semantics/altIdentifier/url/doi.org/10.1088/2632-2153/abd51d
dc.rights.none.fl_str_mv info:eu-repo/semantics/openAccess
info:ar-repo/semantics/accesoabierto
https://creativecommons.org/licenses/by/4.0/
eu_rights_str_mv openAccess
rights_invalid_str_mv info:ar-repo/semantics/accesoabierto
https://creativecommons.org/licenses/by/4.0/
dc.format.none.fl_str_mv application/pdf
dc.source.none.fl_str_mv reponame:Repositorio Institucional Digital de Acceso Abierto
instname:Universidad Nacional Arturo Jauretche
reponame_str Repositorio Institucional Digital de Acceso Abierto
collection Repositorio Institucional Digital de Acceso Abierto
instname_str Universidad Nacional Arturo Jauretche
repository.name.fl_str_mv Repositorio Institucional Digital de Acceso Abierto - Universidad Nacional Arturo Jauretche
repository.mail.fl_str_mv repositorio@unaj.edu.ar
_version_ 1877866016502972416
score 12.823554