| Revista: | Maderas : ciencia y tecnología |
| Base de datos: | |
| Número de sistema: | 000534488 |
| ISSN: | 0718-221X |
| Autores: | Rodrigues de Oliveira, Ricardo1 Ferreira Rodrigues, Larissa2 Mari, João Fernando2 Coelho Naldi, Murilo3 Gomes Milagres, Emerson1 Rocha Vital, Benedito1 Oliveira Carneiro, Angélica de Cássia1 Breda Binoti, Daniel Henrique4 Lopes, Pablo Falco4 Garcia Leite, Helio1 |
| Instituciones: | 1Federal University of Viçosa Department of Forest Engineering, Viçosa MG. Brasil 2Federal University of Viçosa Institute of Exact and Technological Sciences, Rio Paranaíba MG. Brasil 3Federal University of São Carlos Department of Computer Science, São Carlos SP. Brasil 4DAP Florestal, Serra ES. Brasil |
| Año: | 2021 |
| Volumen: | 23 |
| País: | Chile |
| Idioma: | Inglés |
| Resumen en inglés | The differentiation between the charcoal produced from (Eucalyptus) plantations and native forests is essential to control, commercialization, and supervision of its production in Brazil. The main contribution of this study is to identify the charcoal origin using macroscopic images and Deep Learning Algorithm. We applied a Convolutional Neural Network (CNN) using VGG-16 architecture, with preprocessing based on contrast enhancement and data augmentation with rotation over the training set images. on the performance of the CNN with fine-tuning using 360 macroscopic charcoal images from the plantation and native forests. The results pointed out that our method provides new perspectives to identify the charcoal origin, achieving results upper 95 % of mean accuracy to classify charcoal from native forests for all compared preprocessing strategies. |
| Keyword: | Charcoal, Classification, Deep learning, Native wood, Preprocessing. |
| Texto completo: | Texto completo (Ver HTML) Texto completo (Ver PDF) |
