CLASSIFICATION OF Phaseolus lunatus L. USING IMAGE ANALYSIS AND MACHINE LEARNING MODELS

Authors

DOI:

https://doi.org/10.1590/1983-21252022v35n404rc

Keywords:

Artificial intelligence. Image processing. Seeds.

Abstract

Image analysis combined with machine learning models can be an excellent tool for classification of fava (Phaseolus lunatus L.) genotypes and is a low-cost system. Fava is grown by family farmers, mainly, in the Northeast and South regions of Brazil, presenting economic and social importance. Evaluations to gather information on qualitative and quantitative characters of seeds enable the description and distinction of genotypes, allowing the evaluation of variability of plant species, which is essential in breeding programs. The use of image analysis is a fast and economic tool for obtaining large quantity of information. Machine learning techniques have been developed and implemented in the agricultural sector due to technological advances and increasing use of artificial intelligence, which enables the automatization of several processes. In this context, the objective of this work was to evaluate different machine learning models to classify fava genotypes, using data obtained through image analysis. Images of fava seeds were captured using a table scanner (HP Scanjet 2004), set to true color mode, arranged upside down inside of an aluminum box fully closed during the capture of the images for an adequate illumination and prevention of environmental noises. The K-Nearest Neighbor, Naive Bayes, Linear Discriminant Analysis, Support Vector Machine, Gradient Boosting, Bootstrap Aggregating, Classification and Regression Trees, Random Forest, and C50 models were used for the study. Linear Discriminant Analysis was the model that presented the highest efficiency for classifying the genotypes, with an accuracy of 90%.

Downloads

Download data is not yet available.

References

ABUD, H. F. et al. Image analysis of the seeds and seedlings of Vigna radiata L. Revista Ciência Agronômica, 53: 1-9, 2022.

ADVÍNCULA, T. L. et al. Qualidade física e fisiológica de sementes de Phaseolus lunatus L. Revista Brasileira de Ciências Agrárias, 10: 341-346, 2015.

ALMEIDA, R. C. et al. Árvore de decisão como ferramenta na classificação de acessos de feijão-fava. Revista Caatinga, 34: 471-478, 2021.

ALTUNTAS, Y; COMERT, Z; KOCAMAZ, A. F. Identification of haploid and diploid maize seeds using convolutional neural networks and a transfer learning approach. Computers and Electronics in Agriculture, 163: 1-11, 2019.

BAEK, J. et al. High throughput phenotyping for various traits on soybean seeds using image analysis. Sensors, 20: 1-9, 2020.

CARLEO, G. et al. Machine learning and the physical sciences. Reviews of Modern Physics, 91: 1-47, 2019.

CARMO, M. S. et al. Avaliação de acessos de feijão-fava, para resistência a Colletotrichum truncatum, em condições de folhas destacadas e campo. Summa Phytopathologica, 41: 292-297, 2015.

CUNHA, M. A; COSTA, S. M. F. Mapeamento da palmeira de açaí (Euterpe oleracea Mart.) na floresta Amazônica utilizando imagem de satélite de alta resolução espacial. Revista Espinhaço, 9: 40-49, 2020.

ELMASRY, G. et al. Utilization of computer vision and multispectral imaging techniques for classification of cowpea (Vigna unguiculata) seeds. Plant Methods, 15: 1-16, 2019.

HOLANDA, M. E. S. et al. Aplicação de aprendizado de máquina profundo para detecção por imagens de doenças em frutos do cacaueiro. International Journal of Development Research, 11: 47378-47384, 2021.

IBGE – Instituto Brasileiro de Geografia e Estatística. Produção de Fava. Disponível em: <https://www.ibge.gov.br/explica/producao-agropecuaria/fava/br>. Acesso em: 11 jun. 2020.

KAYABASI, A. et al. Automatic classification of agricultural grains: Comparison of neural networks. Neural Network World, 28: 213-224, 2018.

KOKLU, M.; SARIGIL, S.; OZBEK, O. The use of machine learning methods in classification of pumpkin seeds (Cucurbita pepo L.). Genetic Resources and Crop Evolution, 68: 2713-2726, 2021.

LIMA, L. F. et al. Manejo de recursos genéticos vegetais. Anais da Academia Pernambucana de Ciência Agronômica, 15: 109-126, 2018.

LODDO, A.; LODDO, M.; DI RUBERTO, C. A novel deep learning based approach for seed image classification and retrieval. Computers and Electronics in Agriculture, 187: 1-11, 2021.

MEDEIROS, A. D. et al. Interactive machine learning for soybean seed and seedling quality classification. Scientific reports, 10: 1-10, 2020a.

MEDEIROS, A. D. et al. Quality classification of Jatropha curcas seeds using radiographic images and machine learning. Industrial Crops and Products, 146, 1-7, 2020b.

MEDEIROS, A. D.; PEREIRA, M. D.; SILVA, J. A. Processamento digital de imagens na determinação do vigor de sementes de milho. Revista Brasileira de Ciências Agrárias, 13: 1-7, 2018.

MOREIRA, I. B. et al. Separation of coriander seeds by Red, Green and Blue image processing. Ciência Rural, 52: 1-7, 2022.

MORETI, M. P. et al. Inteligência Artificial no Agronegócio e os Desafios para a Proteção da Propriedade Intelectual. Cadernos de Prospecção, 14: 60-77, 2021.

PERINI, L. J. et al. Diversidade genética entre acessos de soja tipo alimento com base no algoritmo de Gower. Colloquium Agrariae, 14: 47-57, 2018.

PONCE, R. M. et al. Tamanho da semente e potencial fisiológico de trigo sarraceno. Revista Científica Rural, 21: 259-268, 2019.

RAMOS, J. L. C. et al. Um estudo comparativo de classificadores na previsão da evasão de alunos em EAD. In: VII CONGRESSO BRASILEIRO DE INFORMÁTICA NA EDUCAÇÃO, 2018, Fortaleza. Anais... Porto Alegre: SBIE, 2018. p. 1463-1472.

REGO, C. H. Q. et al. Using multispectral imaging for detecting seed-borne fungi in cowpea. Agriculture, 10: 1-12, 2020.

SILVA, W. I.; DULTRA FILHO, J. A. Avaliação de caracteres agronômicos e genéticos em acessos de feijão fava no município de Pombal, no semiárido paraibano. In: XV CONGRESSO DE INICIAÇÃO CIENTÍFICA DA UNIVERSIDADE FEDERAL DE CAMPINA GRANDE, 2018, Campina Grande. Anais... Campina Grande: XV CICUFCG, 2018. p. 1-5.

SOARES, L. A. C. Conservação on farm e avaliação agronômica de variedades crioulas de feijão-fava. 2018. 94 f. Dissertação (Mestrado em Agronomia: Área de concentração: Agricultura Tropical) - Universidade Federal do Piauí, Teresina, 2018.

SOUSA, C. A. F. et al. Nova abordagem para a fenotipagem de plantas: conceitos, ferramentas e perspectivas. Revista Brasileira de Geografia Física, 8: 660-672, 2015.

SOYEURT, H. et al. A comparison of 4 different machine learning algorithms to predict lactoferrin content in bovine milk from mid-infrared spectra. Journal of dairy science, 103: 11585-11596, 2020.

TORRES, G. X. Diversidade genética em população segregante de Passiflora via características de sementes. 2018. 82 f. Dissertação (Mestrado em Produção vegetal) – Universidade Estadual do Norte Fluminense, Rio de Janeiro, 2018.

VASCONCELOS, M. C. et al. Radiography and biometric analysis of broadleaf vegetable seeds. Revista de Ciências Agrárias, 61: 1-9, 2018.

WANG, J. et al. Theta-modulated generation of chromatic orbital angular momentum beams from a white-light source. Optics Express, 24: 1-6, 2016.

WANG, T. et al. A feasible image-based colorimetric assay using a smartphone RGB camera for point-of-care monitoring of diabetes. Talanta, 206: 1-5, 2020.

Downloads

Published

20-09-2022

Issue

Section

Agronomy