Commenced in January 2007
Frequency: Monthly
Edition: International
Paper Count: 32295
A Neural Network Classifier for Estimation of the Degree of Infestation by Late Blight on Tomato Leaves

Authors: Gizelle K. Vianna, Gabriel V. Cunha, Gustavo S. Oliveira


Foliage diseases in plants can cause a reduction in both quality and quantity of agricultural production. Intelligent detection of plant diseases is an essential research topic as it may help monitoring large fields of crops by automatically detecting the symptoms of foliage diseases. This work investigates ways to recognize the late blight disease from the analysis of tomato digital images, collected directly from the field. A pair of multilayer perceptron neural network analyzes the digital images, using data from both RGB and HSL color models, and classifies each image pixel. One neural network is responsible for the identification of healthy regions of the tomato leaf, while the other identifies the injured regions. The outputs of both networks are combined to generate the final classification of each pixel from the image and the pixel classes are used to repaint the original tomato images by using a color representation that highlights the injuries on the plant. The new images will have only green, red or black pixels, if they came from healthy or injured portions of the leaf, or from the background of the image, respectively. The system presented an accuracy of 97% in detection and estimation of the level of damage on the tomato leaves caused by late blight.

Keywords: Artificial neural networks, digital image processing, pattern recognition.

Digital Object Identifier (DOI):

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2411


[1] IBGE (Instituto Brasileiro de Geografia e Estatística). Sistema IBGE de Recuperação Automática - SIDRA, Retrieved from, in October 18, 2016.
[2] MAPA (Ministério da Agricultura Pecuária e Abastecimento), Estatísticas e Dados Básicos de Economia Agrícola, Retrieved from, in October 10, 2016.
[3] E. M. Neves, L. Rodrigues, M. Dayoub, and D. S. Dragone, “Bataticultura: dispêndios com defensivos agrícolas no quinquênio 1997-2001,” Batata Show, vol. 6, pp. 22-23, 2003.
[4] F. Zamberlan, et al., “Produção e manejo agrícola: impactos e desafios para sustentabilidade ambiental,” Engenharia Sanitária Ambiental, Edição Especial, pp. 95-100, 2014.
[5] F. C. Bauer and F. M. Vargas Jr., "Fitossanidade e produção agrícola," Produção e Gestão Agroindustrial. Campo Grande: UNIDERP: ch. 44, 2005.
[6] D. Tilman, et al., "Agricultural sustainability and intensive production practices," Nature, Aug 8, 418(6898), pp.: 671-677, 2002.
[7] E. Rembialkowska, “Quality of plant products from organic agriculture,” J. Sci. Food Agric., vol. 87, pp.:2757–2762, 2007.
[8] E.S.G. Mizubuti, J.M.N. Maziero, L.A. Maffia, F. Haddad, and M.A Lima, “CGTE Program: Simulation, Epidemiology and Management of Late Blight,” in Global Initiative on Late Blight Conference, Hamburg, Germany, 2002.
[9] USDA (United States Department of Agriculture), USABlight Project, Retrieved from, in October 4, 2016.
[10] W.F. Becker, “Validação de dois sistemas de previsão para o controle da requeima do tomateiro na região de Caçador, SC,” Agropecuária Catarinense, vol.18, pp. 63-68, 2005.
[11] A. Saxena, B.K. Sarma, and H.B. Singh, “Effect of Azoxystrobin Based Fungicides in Management of Chilli and Tomato Diseases,” Proced. National Academy of Sciences, India: Springer, 2014.
[12] O. Goufo, T. Mofor, and D. Ngnokam, “High Efficacy of Extracts of Cameroon Plants Against Tomato Late Blight Disease,” Agronomy for Sustainable Development, vol. 8, INRA, EDP Sciences, pp.567-573, 2008.
[13] G.K. Vianna and S.M.S. Cruz, “Análise inteligente de imagens digitais no monitoramento da requeima em tomateiros,” Anais do IX Congresso Brasileiro de Agroinformática. Cuiabá, Brazil, 2013.
[14] G.K. Vianna and S.M.S. Cruz, “Redes neurais artificiais aplicadas ao monitoramento da requeima em tomateiros,” Anais do X Encontro Nacional de Inteligência Artificial e Computacional (ENIAC), Fortaleza, Brazil, 2013.
[15] D. Nunes, C. Werly, G.K. Vianna, and S.M.S. Cruz. “Early Discovery of Tomato Foliage Diseases Based on Data Provenance and Pattern Recognition,” 5th International Provenance and Annotation Workshop (IPAW). Cologne, Germany, 2014.
[16] N. Zhanga, M. Wangb, and N. Wanga, “Precision agriculture-a worldwide overview,” Computers and Electronics in Agriculture. vol. 36, issues 2-3, pp.:113-132, 2002.
[17] B.M. Whelan, A.B. McBratney, and B.C. Boydell, “The Impact of Precision Agriculture”. Proceedings of the ABARE Outlook Conference: ‘The Future of Cropping in NW NSW’, p. 5, Moree, UK, 1997.
[18] S. Sankaran, A. Mishraa, R. Ehsani, and C. Davis, “A review of advanced techniques for detecting plant diseases,” Computers and Electronics in Agriculture, vol. 72, n.1, pp.:1-13, 2010.
[19] A.K. Mahlein, E.-C. Oerke, U. Steiner, and H.-W. Dehne, “Recent advances in sensing plant diseases for precision crop protection,” European Journal of Plant Pathology, vol. 133, n.1, pp.:197-209, 2012.
[20] R. Bugiani, et al., “Monitoring airborne concentrations of sporangia of Phytophthora infestans in relation to tomato late blight in Emilia Romagna, Italy,” International Journal of Aerobiology, vol. 11, pp.:41-46, Elsevier Science, 1995.
[21] F.M. Correa, J.S.S. Bueno Filho, and M.G.F. Carmo, “Comparison of three diagrammatic keys for the quantification of late blight in tomato leaves,” Plant Pathology, vol. 58, pp.:1128-1133,2009.
[22] J.R. Macedo, C.L. Capeche, A. Melo da S., and S.B. Bhering, “Recomendações Técnicas para a Produção do Tomate Ecologicamente Cultivado,” Manejo do Solo - Circular Técnica, vol. 33. Rio de Janeiro: Embrapa Solos, 2005.
[23] F.A.R. Filgueira, O novo manual de olericultura, 3rd ed., Viçosa: Editora da UFV, 2008.
[24] J.C.A. Barbedo, “Digital image processing techniques for detecting, quantifying and classifying plant diseases,” SpringerPlus, 2:660, 2013.
[25] A. Vibhute and S.K. Bodhe, “Applications of image processing in agriculture: a survey,” International Journal of Computer Applications, vol. 52, n.2, pp.:34-40, 2012.
[26] R. Zwiggelaar, “A review of spectral properties of plants and their potential use for crop/weed discrimination in row-crops,” Crop Protect, vol. 17 (3), pp.:189–206, 1998.
[27] R.B. Brown and S.D. Noble, “Site-specific weed management: sensing requirements—what do we need to see?,” Weed Sci., vol. 53, pp.:252–258, 2005.
[28] I.M. Scotford and P.C.H. Miller, “Applications of spectral reflectance techniques in Northern European cereal production: a review,” Biosyst. Eng., vol. 90, n.3, pp.:235–250, 2005.
[29] C.H. Bock, G.H. Poole, P.E. Parker, and T.R. Gottwald, “Plant disease severity estimated visually, by digital photography and image analysis, and by hyperspectral imaging,” Critical Reviews in Plant Sciences, vol. 29, n. 1-3, pp.:59–107, 2010.
[30] M.S. Nixon and A.S Aguado, Feature Extraction and Image Processing, 2nd Ed, Elsevier Ltd, 2008.
[31] H. Freeman, “Boundary encoding and processing,” Picture Processing and Psychopictorics, B.S. Lipkin and A. Rosenfeld, Editors, Academic Press: New York, pp. 241-266, 1970.
[32] R.C. Gonzalez and R.E. Woods, Digital Image Processing, 3rd Ed, Prentice-Hall, 2008.
[33] A. Conci, E. Azevedo and F.R. Leta, Computação Gráfica. Teoria e Prática. Rio de Janeiro: Ed. Campus, vol 2, 2007.
[34] Sevarac, Z. “Neuroph - Java neural network framework”. Retrieved from, in January, 2012.
[35] G.K. Vianna and A.C. Thomé, “Neuro-fuzzy system for diagnosis of engines, based on oil aamples analysis,” Annals of 4th World Multiconference on Systemics, Cybernetics and Informatics, Florida, USA, pp.290-295, 2000.
[36] C. Zhang, et al. “Fine mapping of the Ph-3 gene conferring resistance to late blight (Phytophthora infestans) in tomato,” Theor. Appl. Genet., vol. 126, Springer-Verlag, pp.:2643-2653, 2013.
[37] D.H. Park, Y. Zhang, and B.S. Kim, “Improvement of resistance to late blight in hybrid tomato,” Hort. Environm. Biotechnol, vol. 55(2), Springer, pp.:120-124, 2014.