Detection of citrus canker and Huanglongbing using fluorescence imaging spectroscopy and support vector machine technique

Autor(es)

Wetterich, Caio Bruno ; de Oliveira Neves, Ruan Felipe ; Belasque, Jose ; Marcassa, Luis Gustavo

• Tipo de documento: Artigo Científico
• Fonte: APPLIED OPTICS; v. 55, n. 2, p. 8-pg., 2016-01-10.

Resumo

Citrus canker and Huanglongbing (HLB) are citrus diseases that represent a serious threat to the citrus production worldwide and may cause large economic losses. In this work, we combined fluorescence imaging spectroscopy (FIS) and a machine learning technique to discriminate between these diseases and other ordinary citrus conditions that may be present at citrus orchards, such as citrus scab and zinc deficiency. Our classification results are highly accurate when discriminating citrus canker from citrus scab (97.8%), and HLB from zinc deficiency (95%). These results show that it is possible to accurately identify citrus diseases that present similar symptoms. (C) 2016 Optical Society of America (AU)

• Processo FAPESP: 11/22275-6 - Imagem de Fluorescência Usando Filtro Variável de Cristal Liquido em Doenças de Citros
• Beneficiário: Caio Bruno Wetterich
• Modalidade de apoio: Bolsas no Brasil - Doutorado
• Processo FAPESP: 10/16536-9 - Imagem de Fluorescência Aplicada em Doenças de Citros no Campo
• Beneficiário: Luis Gustavo Marcassa
• Modalidade de apoio: Auxílio à Pesquisa - Regular