Diagnofomil: tool for diagnosis of fungal diseases in corn leaf

Authors

DOI:

https://doi.org/10.5965/2764747102042013125

Keywords:

corn diseases, computer vision, neural networks

Abstract

This paper presents the development of a tool for diagnosis of fungal diseases in corn leaves. The tool uses techniques of image processing and computer vision to extract the characteristics from images. These characteristics are extracted using threshold segmentation over the H plane of the image in the HSV color model, highlighting the disease spot. Given the disease spots, their Hu moments are calculated and used as inputs to a neural network. To make the diagnosis a multilayer perceptron neural network is used. Backpropagation is used for the network training. The system achieved an acceptable level of accuracy, diagnosing correctly 100% of the White Spot disease samples, 80% of the Cercospora samples and 80% of the Anthracnose samples.

Downloads

Download data is not yet available.

Author Biographies

Eduardo Stahnke, Santa Catarina State University, UDESC, Brazil.

Specialist in Technologies for Web Applications from the Northern Paraná University, UNOPAR, Brazil.

Graduated in Information Systems at the Santa Catarina State University, UDESC, Brazil.

Professor at the Federal Institute of Santa Catarina - Campus Ibirama, IFC, Brazil.

Fernando dos Santos, Santa Catarina State University, UDESC, Brazil.

PhD in Computing Sciences from the Rio Grande do Sul Federal University, UFRGS, Brazil.

Has a Master’s degree in Computing Sciences, Artificial Intelligence, from the Rio Grande do Sul Federal University, UFRGS

Graduated in Computing Sciences at the Blumenau Regional University Foundation, FURB, Brazil.

Assistant Professor at the Santa Catarina State University, UDESC, Brazil.

References

BORTOLINI, Alexandre M. M. GHELLER, Jorge A. Aplicação de Diferentes Fungicidas no Controle de Doenças Foliares na Cultura do Milho em relação à Produtividade. 2011. Disponível em: http://www.fag.edu.br/novo/arquivos/revista/rbe/1-2011/Artigo_10_2011.pdf. Acesso em: 01 mar. 2012.

CHACON, Germano. ALBUQUERQUE, Marcelo de. ALBUQUERQUE, Marcio. GASTARDELLI, Elton. MORAES, Fernanda. OLIVEIRA, Gabriel. Aplicação da Técnica de Momentos Invariantes no Reconhecimento de Padrões em Imagens Digitais. 2011. Disponível em: http://cbpfindex.cbpf.br/publication_pdfs/nt00611.2011_11_01_09_51_20.pdf. Acesso em: 08 out. 2013.

CONCI, Aura. AZEVEDO, Eduardo. LETA, Fabiana R. Computação Gráfica: Teoria e Prática. Rio de Janeiro: Campus, 2008. 407 p. 2 v.

COPPIN, Bem. Inteligência Artificial. Rio de Janeiro: LTC, 2010. 636 p.

COSTA, Rodrigo V. da. CASELA, Carlos R. COTA, Luciano V. Cultivo do Milho. 5. ed. 2009. Disponível em: http://www.cnpms.embrapa.br/publicacoes/milho_5_ed/doencas.htm. Acesso em: 09 abr. 2012.

GONZALES, Rafael C. WOODS, Richard E. Processamento de Imagens. Trad: Roberto Marcondes Cesar Junior. São Paulo: Editora Edgar Blücher LTDA. 2000. 591 p.

HAYKIN, Simon. Redes Neurais: Princípios e Práticas. 2. ed. Trad: Paulo Martins Engel. Porto Alegre: Bookman, 2001. 900 p.

MARENGONI, Maurício. STRINGHINI, Denise. Tutorial: Introdução à Visão Computaacional Usando OpenCv. 2009. Disponível em: http://seer.ufrgs.br/rita/article/view/rita_v16_n1_p125. Acesso em: 26 jul. 2013.

PINTO, Nicésio F. J de A. Controle Químico de Doenças Foliares em Milho. 2004. Disponível em: http://rbms.cnpms.embrapa.br/index.php/ojs/article/view/96/97. Acesso em: 08 abr. 2012.

RUSSELL, Stuart. NORVIG, Peter. Inteligência Artificial. Trad: Publicare Consultoria. Rio de Janeiro: Elsevier, 2004. 1021 p.

SZELISKI, Richard. Computer Vision: Algorithms and Applications. Trad: Próprio Autor. 2010. Disponível em: http://szeliski.org/Book/. Acesso em: 26 jul. 2013.

VAHLDICK, Adilson. Inteligência Artificial. 2012. Notas de Aula.

Downloads

Published

2013-12-20

How to Cite

Stahnke, E., & Santos, F. dos. (2013). Diagnofomil: tool for diagnosis of fungal diseases in corn leaf. Revista Brasileira De Contabilidade E Gestão, 2(4), 125–136. https://doi.org/10.5965/2764747102042013125

Issue

Vol. 2 No. 4 (2013)

Section

Articles

License

Copyright (c) 2015 Eduardo Stahnke, Fernando dos Santos

Creative Commons License

This work is licensed under a Creative Commons Attribution 4.0 International License.

Brazilian Journal of Accounting and Management offers free and immediate access to its content, following the principle that providing scientifical knowledge in a free manner promotes a better world democratization of knowledge. Authors maintain copyright of articles and grant to the journal the rights of the first publication, according to the Creative Commons Attribution licensing criteria, which allows the work to be shared with initial publication and authorship recognition. These licenses allow others to distribute, remix, adapt, or create derived work, even if it is for commercial purposes, provided that the credit is given to the original creation.