Use este identificador para citar ou linkar para este item: http://www.alice.cnptia.embrapa.br/alice/handle/doc/1052112
Título: Classification of apple tree disorders using Convolutional Neural Networks.
Autoria: NACHTIGALL, L. G.
ARAUJO, R. M.
NACHTIGALL, G. R.
Afiliação: GILMAR RIBEIRO NACHTIGALL, CNPUV.
Ano de publicação: 2016
Referência: In: INTERNATIONAL CONFERENCE ON TOOLS WITH ARTIFICIAL INTELLIGENSE, 28., 2016, San Jose, United States. Anais...San Jose, United States: IEEE, Paper Submission 127, p. 472-476, 2016.
Conteúdo: Abstract?This paper studies the use of Convolutional Neural Networks to automatically detect and classify diseases, nutritional deficiencies and damage by herbicides on apple trees from images of their leaves. This task is fundamental to guarantee a high quality of the resulting yields and is currently largely performed by experts in the field, which can severely limit scale and add to costs. By using a novel data set containing labeled examples consisting of 2539 images from 6 known disorders, we show that trained Convolutional Neural Networks are able to match or outperform experts in this task, achieving a 97.3% accuracy on a hold-out set.
Thesagro: Maca
Palavras-chave: Macieira
Redes neurais
Convolutional Neural Networks
Diseases
Nutritional deficiencies
Damage
Apple trees
Herbicide
Tipo do material: Artigo em anais e proceedings
Acesso: openAccess
Aparece nas coleções:Artigo em anais de congresso (CNPUV)

Arquivos associados a este item:
Arquivo Descrição TamanhoFormato 
NachtigallIEE282016472476.pdf219,41 kBAdobe PDFThumbnail
Visualizar/Abrir

FacebookTwitterDeliciousLinkedInGoogle BookmarksMySpace