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

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 compu...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Giambelluca, Francisco Luis, Cappelletti, Marcelo Angel, Osio, Jorge Rafael, Giambelluca, Luis Alberto
Formato: Articulo
Lenguaje:Inglés
Publicado: 2021
Materias:
Ingeniería
data augmentation
local binary pattern
Machine learning
scorpion image classification
Transfer learning
Acceso en línea:http://sedici.unlp.edu.ar/handle/10915/125115
Aporte de:
SEDICI (UNLP) de Universidad Nacional de La Plata
id I19-R120-10915-125115
record_format dspace
institution Universidad Nacional de La Plata
institution_str I-19
repository_str R-120
collection SEDICI (UNLP)
language Inglés
topic Ingeniería
data augmentation
local binary pattern
Machine learning
scorpion image classification
Transfer learning
spellingShingle Ingeniería
data augmentation
local binary pattern
Machine learning
scorpion image classification
Transfer learning
Giambelluca, Francisco Luis
Cappelletti, Marcelo Angel
Osio, Jorge Rafael
Giambelluca, Luis Alberto
Novel automatic scorpion-detection and -recognition system based on machine-learning techniques
topic_facet Ingeniería
data augmentation
local binary pattern
Machine learning
scorpion image classification
Transfer learning
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): <i>Bothriurus bonariensis</i> (of no sanitary importance), <i>Tityus trivittatus</i>, and <i>Tityus confluence</i> (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 <i>Tityus</i> and <i>Bothriurus</i> (for health security) and between <i>T. trivittatus</i> and <i>T. confluence</i> (for biological research purposes).
format Articulo
Articulo
author Giambelluca, Francisco Luis
Cappelletti, Marcelo Angel
Osio, Jorge Rafael
Giambelluca, Luis Alberto
author_facet Giambelluca, Francisco Luis
Cappelletti, Marcelo Angel
Osio, Jorge Rafael
Giambelluca, Luis Alberto
author_sort Giambelluca, Francisco Luis
title Novel automatic scorpion-detection and -recognition system based on machine-learning techniques
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
publishDate 2021
url http://sedici.unlp.edu.ar/handle/10915/125115
work_keys_str_mv AT giambellucafranciscoluis novelautomaticscorpiondetectionandrecognitionsystembasedonmachinelearningtechniques
AT cappellettimarceloangel novelautomaticscorpiondetectionandrecognitionsystembasedonmachinelearningtechniques
AT osiojorgerafael novelautomaticscorpiondetectionandrecognitionsystembasedonmachinelearningtechniques
AT giambellucaluisalberto novelautomaticscorpiondetectionandrecognitionsystembasedonmachinelearningtechniques
bdutipo_str Repositorios
_version_ 1764820450059223040

Ejemplares similares