A review on the main challenges in automatic plant disease identification based on visible range images

Autor(es)

Arnal Barbedo, Jayme Garcia

• Tipo de documento: Artigo de Revisão
• Fonte: BIOSYSTEMS ENGINEERING; v. 144, p. 52-60, APR 2016.
• Citações Web of Science: 46

Resumo

The problem associated with automatic plant disease identification using visible range images has received considerable attention in the last two decades, however the techniques proposed so far are usually limited in their scope and dependent on ideal capture conditions in order to work properly. This apparent lack of significant advancements may be partially explained by some difficult challenges posed by the subject: presence of complex backgrounds that cannot be easily separated from the region of interest (usually leaf and stem), boundaries of the symptoms often are not well defined, uncontrolled capture conditions may present characteristics that make the image analysis more difficult, certain diseases produce symptoms with a wide range of characteristics, the symptoms produced by different diseases may be very similar, and they may be present simultaneously. This paper provides an analysis of each one of those challenges, emphasizing both the problems that they may cause and how they may have potentially affected the techniques proposed in the past. Some possible solutions capable of overcoming at least some of those challenges are proposed. (C) 2016 IAgrE. Published by Elsevier Ltd. All rights reserved. (AU)

• Processo FAPESP: 13/06884-8 - Diagnóstico automático de doenças em plantas usando imagens digitais
• Beneficiário: Jayme Garcia Arnal Barbedo
• Modalidade de apoio: Auxílio à Pesquisa - Regular