Development of a Mobile Application for the Identification of Foliar Diseases in Agricultural Crops
DOI:
https://doi.org/10.22481/recic.v8i1.18520Keywords:
Foliar plant diseases, artificial neural networks, computer vision, APIs, mobile applicationsAbstract
The growing need to reduce agricultural losses caused by pests and diseases, combined with the increasing demand for food, has driven the search for new techniques and technologies capable of supporting farmers. To assist smallholder farmers in the rapid and accurate identification of foliar diseases in plants, an application called KAWARI was developed using computer vision and artificial neural networks. The application analyzes images captured by users and provides a diagnosis, along with additional information about the disease, nearby outbreak locations, recommended treatment products, and local suppliers. The model was trained using the PlantVillage dataset, which contains images of diseased apple and grapevine leaves. To enhance the model’s robustness and expand the dataset, image preprocessing techniques were applied, including brightness and contrast adjustments, rotation, and zooming. In parallel, a Node.js API was developed to enable communication between the application and the artificial neural network, while the mobile application was implemented using React Native. Communication among the application, the API, and the neural network proved efficient, and the model achieved a performance rate of 98.63% in image diagnosis. This study demonstrates the potential of computer vision as an agricultural support tool, enabling the rapid and accurate detection of plant diseases.
Downloads
References
FAO Frear as pragas e as doenças das plantas, FAO, 2015.
C. M. OLIVEIRA, A. M. AUADA, S. M. MENDES, e M. R. FRIZZAS. "Crop losses and the economic impact of insect pests on brazilian agriculture," Crop Protection, vol. 56, pp. 50-54, 2014.
OECD/FAO perspectivas agrícolas 2023-2032.," OECD/FAO, p. 391, 2023.
S. M. FONSECA, S. MASSRUHÁ, A. de Andrade LEITE, e Édson Luis BOLFE, AGRO 4.0. Rio de Janeiro: Autografia, 2023.
K. SCHWAB, A QUARTA REVOLUÇÃO INDUSTRIAL. Edipro, 1 ed., 2018.
D. C. ROSE e J. CHILVERS, "Agriculture 4.0," Frontiers in Sustainable Food Systems, vol. 2, 2018.
J. B. SACOMANO, R. F. GONÇALVES, M. T. da SILVA, S. H. BONILLA, e V. C. SATYRO, INDUSTRIA 4.0. São Paulo: Edgard Blucher, I ed., 2018.
M. R. BORTH, J. C. IACIA, H. PISTORI, e C. F. RUVIARO, "A visão computacional do agronegócio," 7º Encontro Científico de Administração, Economia e Contabilidade (ECAECO), 2014.
T. M. MITCHELL, MACHINE LEARNING. New York: McGraw-Hill Education, 1 ed., 1997.
K. FACELI, A. C. LORENA, J. GAMA, e A. C. P. L. F. CARVALHO, INTELIGÊNCIA ARTIFICIAL. Rio de Janeiro: LTC, 2011.
J. R. JANG, C. SUN, e E. MIZUTANI, NEURO-FUZZY AND SOFT COMPUTING. Londres: Prentice-Hall, 1997.
S. HAYKIN, REDES NEURAIS. São Paulo: Bookman, 2 ed., 2001.
W. S. MCCULLOCH e W. PITTS, "A logical calculus of the ideas immanent in nervous activity." Bulletin of Mathematical Biophysics, vol. 5, no. 4, pp. 115-133, 1943.
L. N. d. Silva, D. H. Spatti, e R. A. Flauzino, Redes neurais artificiais para engenharia e ciências aplicadas. São Paulo: Artliber Editora, 2010.
L. SHAPIRO e G. STOCKMAN, COMPUTER VISION. Londres: Prentice Hall, 1 ed., 2001.
S. RUSSELL e P. NORVIG, INTELIGÊNCIA ARTIFICIAL. Rio de Janeiro: Elsevier, 1 ed., 2004.
E. N. Rosa, "Utilização de redes neurais para reconhecimento de doenças foliares em culturas agrícolas," Universidade Federal de Santa Catarina, 2022.
T. d. M. Leite, "Deep learning em dois estágios para detecção e classificação de doenças em folhas de plantas com aplicação em dispositivos móveis," Dissertação de Mestrado, Universidade de São Paulo, 2021.
V. R. Ferreira e A. M. de Paula Canuto, "Potencializando a classificação de imagens com eficiência e robustez através da fibernet.." Revista de Ciência de Computação, vol. 5, no. 1, pp. 7-20, 2023.
R. G. Carvalho e L. T. Zoby, "Convolutional neural networks for leaf disease classification," em Anais do XV Encontro Nacional de Inteligência Artificial e Computacional, pp. 332-342, SBC, 2018.
F. Funck, "Detectando a ferrugem asiática na folha da soja utilizando redes neurais convolucionais," Monografia de Graduação, Universidade Tecnológica Federal do Paraná, 2019.
M. J. Silva e J. Schimiguel, "Identificação de doenças em plantas por meio de processamento de imagens: redes neurais convolucionais como auxílio à agricultura," Revista de Ubiquidade, vol. 3, no. 1, pp. 91-111, 2020.
A. C. Gil, Métodos e técnicas de pesquisa social. São Paulo: 6. ed. Editora Atlas SA, 2008.
P. Raghav, "Understanding of convolutional neural network (cnn)," 2018.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 Journal of Computer Science

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