Boron Deficiency Precisely Identified on Growth Stage V4 of Maize Crop Using Texture Image Analysis

Autor(es)

Luz, P. H. C. ^[1] ; Marin, M. A. ^[1] ; Devechio, F. F. S. ^[1] ; Romualdo, L. M. ^[1] ; Zuniga, A. M. G. ^[2] ; Oliveira, M. W. S. ^[2] ; Herling, V. R. ^[1] ; Bruno, O. M. ^[2]

Afiliação do(s) autor(es)

^[1] Univ Sao Paulo, FZEA, Coll Anim Sci & Food Engn, Dept Anim Sci, Pirassununga, SP - Brazil

^[2] Univ Sao Paulo, IFSC, Inst Phys Sao Carlos, Dept Phys, Sao Carlos, SP - Brazil

• Tipo de documento: Artigo Científico
• Fonte: Communications in Soil Science and Plant Analysis; v. 49, n. 2, p. 159-169, 2018.
• Citações Web of Science: 1

Resumo

The aim of this study was to evaluate the diagnostic imaging approach to identify the deficiency of boron in leaves of maize. The experiment was conducted in a greenhouse under a hydroponic system. The treatments were four levels of boron (B) in solution nutrition (zero, 0.12, 0.24 and 0.60 mg L-1), combined at V4, V7, and R1 growing stages. Plant parts sampled included index leaf and new leaf to chemical analysis and texture image analysis. Our proposal was to apply these texture analysis and pattern classification schemes to identify the levels of B. Texture methods achieved 98% of accuracy in differentiating between leaves properly fertilized with B, from leaves with deficiency, in V4. In all tests, with index leaf success rate was higher than 80%, and around 90% for the new leaf. The image analysis by texture techniques applied on maize leaves are able to identify boron deficiencies in younger plants. (AU)

• Processo FAPESP: 10/18233-3 - Avaliação do estado nutricional de plantas de milho utilizando o sistema de visão artificial
• Beneficiário: Pedro Henrique de Cerqueira Luz
• Modalidade de apoio: Auxílio à Pesquisa - Regular