Identificação Automática de Vegetais Fósseis Utilizando Visão Computacional
Resumo
O Devoniano marcou o surgimento das primeiras plantas terrestres complexas. Na Bacia do Parnaíba, fósseis desse período revelam aspectos da evolução da flora e do clima. No entanto, a identificação manual desses espécimes é lenta e sujeita a erros, devido a fragmentação e a similaridades morfológicas, o que compromete a precisão e a reprodutibilidade das análises tradicionais. Este estudo propõe o uso de redes neurais para automatizar a identificação de exemplares fósseis vegetais previamente atribuídos ao gênero Haplostigma. Foram utilizadas 140 imagens segmentadas manualmente, com aumento de dados e diferentes arquiteturas de CNNs pré-treinadas. A ResNet50V2 obteve os melhores resultados, com 90% de acurácia e F1-Score, 86,3% de precisão e 95% de recall.Referências
Cleal, C. J. and Thomas, B. A. (2009). An introduction to plant fossils. Cambridge University Press, Cambridge.
Duan, X.-Y. and Gu, S.-M. (2023). Identification of phtato leaf disease based on the ts-resnet deep learing method. In 2023 International Conference on Wavelet Analysis and Pattern Recognition (ICWAPR), pages 19–25.
Dumoulin, V. and Visin, F. (2016). A guide to convolution arithmetic for deep learning. arXiv preprint arXiv:1603.07285.
Fleiss, J. L., Levin, B., and Paik, M. C. (2013). Statistical methods for rates and proportions. john wiley & sons.
Gracioso, D. E. (2011). Icnofósseis de invertebrados da formação pimenteira (devoniano) na borda leste da bacia do parnaíba.
He, K., Zhang, X., Ren, S., and Sun, J. (2016a). Deep residual learning for image recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 770–778.
He, K., Zhang, X., Ren, S., and Sun, J. (2016b). Identity mappings in deep residual networks. In Computer Vision–ECCV 2016: 14th European Conference, Amsterdam, The Netherlands, October 11–14, 2016, Proceedings, Part IV 14, pages 630–645. Springer.
Karaderi, T., Burghardt, T., Hsiang, A. Y., Ramaer, J., and Schmidt, D. N. (2022). Visual microfossil identification via deep metric learning. In El Yacoubi, M., Granger, E., Yuen, P. C., Pal, U., and Vincent, N., editors, Pattern Recognition and Artificial Intelligence, pages 34–46, Cham. Springer International Publishing.
Kenrick, P. and Crane, P. R. (1997). The origin and early evolution of plants on land. Nature, 389:33–39.
Liu, X. and Song, H. (2020). Automatic identification of fossils and abiotic grains during carbonate microfacies analysis using deep convolutional neural networks. Sedimentary Geology, 410:105790.
Matsumura, W. M. K., Di Pasquo, M., Iannuzzi, R., and Bosetti, E. P. (2024). Plant diversification through the devonian in brazil. In Brazilian Paleofloras: From Paleozoic to Holocene, pages 125–202. Springer.
Matsumura, W. M. K. and Iannuzzi, R. (2015). Plantas devonianas do brasil e seu significado bioestratigráfico. Boletim do Museu Paraense Emílio Goeldi-Ciências Naturais, 10(1):19–36.
Mimura, K., Minabe, S., Nakamura, K., Yasukawa, K., Ohta, J., and Kato, Y. (2022). Automated detection of microfossil fish teeth from slide images using combined deep learning models. Applied Computing and Geosciences, 16:100092.
Sandler, M., Howard, A., Zhu, M., Zhmoginov, A., and Chen, L.-C. (2018). Mobilenetv2: Inverted residuals and linear bottlenecks. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 4510–4520.
Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., and Wojna, Z. (2016). Rethinking the inception architecture for computer vision. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 2818–2826.
Wang, B., Sun, R., Yang, X., Niu, B., Zhang, T., Zhao, Y., Zhang, Y., Zhang, Y., and Han, J. (2023). Recognition of rare microfossils using transfer learning and deep residual networks. Biology, 12(1).
Wang, H., Li, C., Zhang, Z., Kershaw, S., Holmer, L. E., Zhang, Y., Wei, K., and Liu, P. (2022). Fossil brachiopod identification using a new deep convolutional neural network. Gondwana Research, 105:290–298.
Willis, K. and McElwain, J. (2002). The Evolution of Plants. Oxford University Press.
Yu, C., Qin, F., Watanabe, A., Yao, W., Li, Y., Qin, Z., Liu, Y., Wang, H., Jiangzuo, Q., Hsiang, A. Y., Ma, C., Rayfield, E., Benton, M. J., and Xu, X. (2024). Artificial intelligence in paleontology. Earth-Science Reviews, 252:104765.
Zhang, B., Xin, C., Yang, D., Jiao, Z., Liu, S., Di, G., and Zhao, H. (2024). Numerical taxonomy and genus-species identification of czekanowskiales in china based on machine learning. Palaeontologia Electronica, 27(1):1–19.
Duan, X.-Y. and Gu, S.-M. (2023). Identification of phtato leaf disease based on the ts-resnet deep learing method. In 2023 International Conference on Wavelet Analysis and Pattern Recognition (ICWAPR), pages 19–25.
Dumoulin, V. and Visin, F. (2016). A guide to convolution arithmetic for deep learning. arXiv preprint arXiv:1603.07285.
Fleiss, J. L., Levin, B., and Paik, M. C. (2013). Statistical methods for rates and proportions. john wiley & sons.
Gracioso, D. E. (2011). Icnofósseis de invertebrados da formação pimenteira (devoniano) na borda leste da bacia do parnaíba.
He, K., Zhang, X., Ren, S., and Sun, J. (2016a). Deep residual learning for image recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 770–778.
He, K., Zhang, X., Ren, S., and Sun, J. (2016b). Identity mappings in deep residual networks. In Computer Vision–ECCV 2016: 14th European Conference, Amsterdam, The Netherlands, October 11–14, 2016, Proceedings, Part IV 14, pages 630–645. Springer.
Karaderi, T., Burghardt, T., Hsiang, A. Y., Ramaer, J., and Schmidt, D. N. (2022). Visual microfossil identification via deep metric learning. In El Yacoubi, M., Granger, E., Yuen, P. C., Pal, U., and Vincent, N., editors, Pattern Recognition and Artificial Intelligence, pages 34–46, Cham. Springer International Publishing.
Kenrick, P. and Crane, P. R. (1997). The origin and early evolution of plants on land. Nature, 389:33–39.
Liu, X. and Song, H. (2020). Automatic identification of fossils and abiotic grains during carbonate microfacies analysis using deep convolutional neural networks. Sedimentary Geology, 410:105790.
Matsumura, W. M. K., Di Pasquo, M., Iannuzzi, R., and Bosetti, E. P. (2024). Plant diversification through the devonian in brazil. In Brazilian Paleofloras: From Paleozoic to Holocene, pages 125–202. Springer.
Matsumura, W. M. K. and Iannuzzi, R. (2015). Plantas devonianas do brasil e seu significado bioestratigráfico. Boletim do Museu Paraense Emílio Goeldi-Ciências Naturais, 10(1):19–36.
Mimura, K., Minabe, S., Nakamura, K., Yasukawa, K., Ohta, J., and Kato, Y. (2022). Automated detection of microfossil fish teeth from slide images using combined deep learning models. Applied Computing and Geosciences, 16:100092.
Sandler, M., Howard, A., Zhu, M., Zhmoginov, A., and Chen, L.-C. (2018). Mobilenetv2: Inverted residuals and linear bottlenecks. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 4510–4520.
Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., and Wojna, Z. (2016). Rethinking the inception architecture for computer vision. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 2818–2826.
Wang, B., Sun, R., Yang, X., Niu, B., Zhang, T., Zhao, Y., Zhang, Y., Zhang, Y., and Han, J. (2023). Recognition of rare microfossils using transfer learning and deep residual networks. Biology, 12(1).
Wang, H., Li, C., Zhang, Z., Kershaw, S., Holmer, L. E., Zhang, Y., Wei, K., and Liu, P. (2022). Fossil brachiopod identification using a new deep convolutional neural network. Gondwana Research, 105:290–298.
Willis, K. and McElwain, J. (2002). The Evolution of Plants. Oxford University Press.
Yu, C., Qin, F., Watanabe, A., Yao, W., Li, Y., Qin, Z., Liu, Y., Wang, H., Jiangzuo, Q., Hsiang, A. Y., Ma, C., Rayfield, E., Benton, M. J., and Xu, X. (2024). Artificial intelligence in paleontology. Earth-Science Reviews, 252:104765.
Zhang, B., Xin, C., Yang, D., Jiao, Z., Liu, S., Di, G., and Zhao, H. (2024). Numerical taxonomy and genus-species identification of czekanowskiales in china based on machine learning. Palaeontologia Electronica, 27(1):1–19.
Publicado
28/05/2025
Como Citar
SILVA, Davi Rodolfo Rodrigues da; ARAÚJO, Mislayne Oliveira de; SANTOS, Maria Vitória Moura; ALVES, Melissa Oliveira; OLIVEIRA, Paulo Victor de; VELOSO E SILVA, Romuere Rodrigues.
Identificação Automática de Vegetais Fósseis Utilizando Visão Computacional. In: ENCONTRO UNIFICADO DE COMPUTAÇÃO DO PIAUÍ (ENUCOMPI), 17. , 2025, Teresina/PI.
Anais [...].
Porto Alegre: Sociedade Brasileira de Computação,
2025
.
p. 159-168.
DOI: https://doi.org/10.5753/enucompi.2025.9785.
