Unconventional food plants recognition: an analysis of classification methods applied to computer vision

• Gustavo Almeida UFOPA
• Virgílio Soares UFOPA
• Marcio Ponte UFOPA
• Fabio Lobato UFOPA

DOI: https://doi.org/10.5753/wcama.2019.6421

Abstract

Amazon forest’s vast biodiversity opens doors to many studies, including the use of computational methods to analyze the fauna and flora. Checking the gap in the study of unconventional edible plants (UEPs) in the western region of Pará, in this work are used computer vision techniques to automatically identify plants belonging to this category. For such a result, we evaluated the use of seven classifiers for recognition in digital images of UEPs. The results showed good accuracy in the recognition of the classes on the test images. As a direct impact of the study, we highlight the possibility of developing a decision support application for automatic recognition of UEPs in order to be used by regulatory institutions.

References

Bezerra, M. E. R. and Oliveira, A. L. I. (2006). M´etodos baseados na regra do vizinho mais pr´oximo para reconhecimento de imagens.

Bredariol, L. R. (2015). Levantamento e caracterizac¸ ˜ao das plantas aliment´ıcias n˜ao con- vencionais (panc’s) espontˆaneas presentes em um sistema agroflorestal no munic´ıpio de rio claro-sp.

Castillo, R., Contreras, D., Freer, J., Ruiz, J., and Valenzuela, S. (2008). Supervised pattern recognition techniques for classification of eucalyptus species from leaves nir spectra. Journal ofthe Chilean Chemical Society, 53(4):1709–1713.

Duarte, G. d. R. (2018). Levantamento e caracterizac¸ ˜ao das plantas aliment´ıcias n˜ao convencionais do Parque Florestal de Monsanto-Lisboa. PhD thesis.

Hoorn, C., Wesselingh, F. P., ter Steege, H., Bermudez, M. A., Mora, A., Sevink, J., Sanmart´ın, I., Sanchez-Meseguer, A., Anderson, C. L., Figueiredo, J. P., Jaramillo, C., Riff, D., Negri, F. R., Hooghiemstra, H., Lundberg, J., Stadler, T., S¨arkinen, T., and Antonelli, A. (2010). Amazonia through time: Andean uplift, climate change, landscape evolution, and biodiversity. Science, 330(6006):927–931.

Hossain, J. and Amin, M. A. (2010). Leaf shape identification based plant biometrics. In 2010 13th International conference on computer and information technology (ICCIT), pages 458–463. IEEE.

Kinupp, V. F. and Lorenzi, H. (2014). Plantas Aliment´ıcias N˜ao Convencionais (PANC) no Brasil: guia de identificacao, aspectos nutricionais e receitas ilustradas. Instituto Plantarum de Estudos da Flora Ltda.

Kumar, M., Kamble, M., Pawar, S., Patil, P., and Bonde, N. (2011). Survey on techniques for plant leaf classification. International Journal of Modern Engineering Research, 1(2):538–544.

Satti, V., Satya, A., and Sharma, S. (2013). An automatic leaf recognition system for plant identification using machine vision technology. International journal of engineering science and technology, 5(4):874.

Sousa, R. d. S., Guedes, E. B., and Oliveira, M. B. L. (2018). Previsao anual de precipitacoes em manaus, amazonas: Um comparativo de tecnicas de aprendizado de m´aquina. In 9o Workshop de Computacao Aplicada a Gestao do Meio Ambiente e Recursos Naturais (WCAMA CSBC 2018), volume 9. SBC.

Visentini, G. C., Pavan, W., Holbig, C. A., and Fernades, J. M. (2018). Aplicativo ios para coleta autˆonoma de imagens e monitoramento do meio agr´ıcola. In 9o Workshop de Computac¸ ˜ao Aplicada a Gest˜ao do Meio Ambiente e Recursos Naturais (WCAMA CSBC 2018), volume 9. SBC.