| |
|
|
 | Acesso ao texto completo restrito à biblioteca da Embrapa Florestas. Para informações adicionais entre em contato com cnpf.biblioteca@embrapa.br. |
|
Registro Completo |
|
Biblioteca(s): |
Embrapa Florestas. |
|
Data corrente: |
11/02/2025 |
|
Data da última atualização: |
11/02/2025 |
|
Tipo da produção científica: |
Artigo em Periódico Indexado |
|
Autoria: |
TACA, B. S.; LAU, D.; RIEDER, R. |
|
Afiliação: |
BRENDA SLONGO TACA, UNIVERSIDADE DE PASSO FUNDO; DOUGLAS LAU, CNPF; RAFAEL RIEDER, UNIVERSIDADE DE PASSO FUNDO. |
|
Título: |
A comparative study between deep learning approaches for aphid classification. |
|
Ano de publicação: |
2025 |
|
Fonte/Imprenta: |
IEEE Latin America Transactions, v. 23, n. 3, p. 198-204, 2025. |
|
ISSN: |
1548-0992 |
|
DOI: |
https://doi.org/10.1109/TLA.2025.10879193 |
|
Idioma: |
Português |
|
Conteúdo: |
This study presents a performance comparison between two convolutional neural networks in the task of detecting aphids in digital images: AphidCV, customized for counting, classifying, and measuring aphids, and YOLOv8, state-of-the-art in real-time object detection. Our work considered 48,000 images for training for six different insect species (8,000 images divided into four classes), in addition to data augmentation techniques. For comparative purposes, we considered evaluation metrics available to both architectures (Accuracy, Precision, Recall, and F1-Score) and additional metrics (ROC Curve and PR AUC for AphidCV; mAP50 and mAP50-95 for YOLOv8). The results revealed an average F1-Score=0.891 for the AphidCV architecture, version 3.0, and an average F1-Score=0.882 for the YOLOv8, medium version, demonstrating the effectiveness of both architectures for training aphid detection models. Overall, AphidCV performed slightly better for the majority of metrics and species in the study, serving its design purpose very well. YOLOv8 proved to be faster to converge the models, with the potential to apply in research considering many aphid species. |
|
Palavras-Chave: |
AphidCV; Aphids; Comparative study; Detecção de objeto; Estudo comparativo; Object detection; Redes neurais. |
|
Thesagro: |
Afídeo; Pulgão. |
|
Thesaurus Nal: |
Neural networks. |
|
Categoria do assunto: |
O Insetos e Entomologia |
|
Marc: |
LEADER 01981naa a2200289 a 4500
001 2172637
005 2025-02-11
008 2025 bl uuuu u00u1 u #d
022 $a1548-0992
024 7 $ahttps://doi.org/10.1109/TLA.2025.10879193$2DOI
100 1 $aTACA, B. S.
245 $aA comparative study between deep learning approaches for aphid classification.$h[electronic resource]
260 $c2025
520 $aThis study presents a performance comparison between two convolutional neural networks in the task of detecting aphids in digital images: AphidCV, customized for counting, classifying, and measuring aphids, and YOLOv8, state-of-the-art in real-time object detection. Our work considered 48,000 images for training for six different insect species (8,000 images divided into four classes), in addition to data augmentation techniques. For comparative purposes, we considered evaluation metrics available to both architectures (Accuracy, Precision, Recall, and F1-Score) and additional metrics (ROC Curve and PR AUC for AphidCV; mAP50 and mAP50-95 for YOLOv8). The results revealed an average F1-Score=0.891 for the AphidCV architecture, version 3.0, and an average F1-Score=0.882 for the YOLOv8, medium version, demonstrating the effectiveness of both architectures for training aphid detection models. Overall, AphidCV performed slightly better for the majority of metrics and species in the study, serving its design purpose very well. YOLOv8 proved to be faster to converge the models, with the potential to apply in research considering many aphid species.
650 $aNeural networks
650 $aAfídeo
650 $aPulgão
653 $aAphidCV
653 $aAphids
653 $aComparative study
653 $aDetecção de objeto
653 $aEstudo comparativo
653 $aObject detection
653 $aRedes neurais
700 1 $aLAU, D.
700 1 $aRIEDER, R.
773 $tIEEE Latin America Transactions$gv. 23, n. 3, p. 198-204, 2025.
Download
Esconder MarcMostrar Marc Completo |
|
Registro original: |
Embrapa Florestas (CNPF) |
|
|
Biblioteca |
ID |
Origem |
Tipo/Formato |
Classificação |
Cutter |
Registro |
Volume |
Status |
URL |
Voltar
|
|
|
| Registros recuperados : 5 | |
| Registros recuperados : 5 | |
|
| Expressão de busca inválida. Verifique!!! |
|
|
