A Comparison Study of Deep Convolutional Neural Networks for the Classification of Brazilian Savannah Pollen Grains: Preliminary Results
Resumo
The classification of pollen grains images are currently done manually and visually, being a weariful task and predisposed to mistakes due to human exhaustion. In this paper, the authors introduce an automatic classification of 55 different pollen grain classes, using convolutional neural networks. Different architectures and hyperparameters were used to improve the classification result. Using the networks VGG16, VGG19, and InceptionV3, were obtained accuracy rates over 93.58%.
Palavras-chave:
Computer vision, Machine Learning, Palynology, Pollen Grains
Referências
Boyain- Goitia, A. R., Beddows, D. C., Griffiths, B. C., and Telle, H. H. ( 2003). Single-pollen analysis by laser-induced breakdown spectroscopy and raman microscopy. Applied Optics, 42 ( 30): 6119 - DOI: 10.1364/ao.42.006119
Collinvaux, P. A., De Oliveira, P. E., and Moreno, E. ( 2014). Amazon: Pollen Manual and Atlas: Pollen Manual and Atlas. CRC Press. DOI: 10.1201/9781482283600
Da Silva, D. S., Quinta, L. N. B., Gonccalves, A., Pistori, H., and Borth, M. R. ( 2014). Application of wavelet transform in the classification of pollen grains. African Journal of Agricultural Research, 9 ( 10): 908 - 913.
Delves, P. J., Martin, S. J., Burton, D. R., and Roitt, I. M. ( 2017). Essential immunology. John Wiley & Sons.
Gonçalves, A. B., Rodrigues, C. N. M., Cereda, M. P., and Pistori, H. ( 2013). Identificacção computadorizada de tipos polínicos através de bag of words. Cadernos de Agroecologia, 8 (2): 1.
Gonçalves, A. B., Souza, J. S., da Silva, G. G., Cereda, M. P., Pott, A., Naka, M. H., and Pistori, H. ( 2016). Feature extraction and machine learning for the classification of brazilian savannah pollen grains. PloS one, 11 (6): e0157044.
Hwang, G. M., Riley, K. C., Christou, C. T., Jacyna, G. M., Woodard, J. P., Ryan, R. M., Bush, M. B., Valencia, B. G., McMichael, C. N., Punyasena, S. W., et al. ( 2013). Automated pollen identification system for forensic geo-historical location applications. In 2013 IEEE International Conference on Technologies for Homeland Security (HST), pages 297 - 303. IEEE. DOI: 10.1109/ths.2013.6699018
Jackson, S. T. and Williams, J. W. ( 2004). Modern analogs in quaternary paleoecology: here today, gone yesterday, gone tomorrow Annu. Rev. Earth Planet. Sci., 32 : 495 - 537. DOI: 10.1146/annurev.earth.32.101802.120435
Joosten, H. and de Klerk, P. ( 2002). What's in a name: Some thoughts on pollen classification, identification, and nomenclature in quaternary palynology. Review of Palaeobotany and Palynology, 122 ( 1-2): 29 - 45.
Kingma, D. P. and Ba, J. ( 2014). Adam: A method for stochastic optimization. arXiv preprint arXiv: 6980.
Nakagawa, T., Edouard, J.-L., and de Beaulieu, J.- L. ( 2000). A scanning electron microscopy (sem) study of sediments from lake cristol, southern french alps, with special reference to the identification of pinus cembra and other alpine pinus species based on sem pollen morphology. Review of Palaeobotany and Palynology, 108 (1-2): 1 - DOI: 10.1016/s0034-6667(99)00030-5
Ng, A. ( 2019). Machine learning yearning: Technical strategy for ai engineers in the era of deep learning. Technical report, Tech. Rep.
Prince, S. J. ( 2012). Computer vision: models, learning, and inference. Cambridge University Press. DOI: 10.1017/cbo9780511996504
Quinta, L. N. B. ( 2013). Visao computacional aplicada na classificacção de graos de pólen. Master's thesis, Programa de Pó s Graduação em Biotecnologia, Universidade Católica Dom Bosco.
Quinta, L. N. B., Amorim, W. P., de Carvalho, M. H., Cereda, M. P., and Pistori, H. ( 2012). Floresta de caminhos ótimos na classificação de pólen. In Workshop de Visão Computacional.
Russakovsky, O., Deng, J., Su, H., Krause, J., Satheesh, S., Ma, S., Huang, Z., Karpathy, A., Khosla, A., Bernstein, M., et al. ( 2015). Imagenet large scale visual recognition challenge. International journal of computer vision, 115 ( 3): 211 - 252. DOI: 10.1007/s11263-015-0816-y
Von Der Ohe, W., Oddo, L., Piana, M., Morlot, M., and Martin, P. ( 2004). Harmonized methods of melissopalynology. 35 : 18 - 25. DOI: 10.1051/apido:2004050
Collinvaux, P. A., De Oliveira, P. E., and Moreno, E. ( 2014). Amazon: Pollen Manual and Atlas: Pollen Manual and Atlas. CRC Press. DOI: 10.1201/9781482283600
Da Silva, D. S., Quinta, L. N. B., Gonccalves, A., Pistori, H., and Borth, M. R. ( 2014). Application of wavelet transform in the classification of pollen grains. African Journal of Agricultural Research, 9 ( 10): 908 - 913.
Delves, P. J., Martin, S. J., Burton, D. R., and Roitt, I. M. ( 2017). Essential immunology. John Wiley & Sons.
Gonçalves, A. B., Rodrigues, C. N. M., Cereda, M. P., and Pistori, H. ( 2013). Identificacção computadorizada de tipos polínicos através de bag of words. Cadernos de Agroecologia, 8 (2): 1.
Gonçalves, A. B., Souza, J. S., da Silva, G. G., Cereda, M. P., Pott, A., Naka, M. H., and Pistori, H. ( 2016). Feature extraction and machine learning for the classification of brazilian savannah pollen grains. PloS one, 11 (6): e0157044.
Hwang, G. M., Riley, K. C., Christou, C. T., Jacyna, G. M., Woodard, J. P., Ryan, R. M., Bush, M. B., Valencia, B. G., McMichael, C. N., Punyasena, S. W., et al. ( 2013). Automated pollen identification system for forensic geo-historical location applications. In 2013 IEEE International Conference on Technologies for Homeland Security (HST), pages 297 - 303. IEEE. DOI: 10.1109/ths.2013.6699018
Jackson, S. T. and Williams, J. W. ( 2004). Modern analogs in quaternary paleoecology: here today, gone yesterday, gone tomorrow Annu. Rev. Earth Planet. Sci., 32 : 495 - 537. DOI: 10.1146/annurev.earth.32.101802.120435
Joosten, H. and de Klerk, P. ( 2002). What's in a name: Some thoughts on pollen classification, identification, and nomenclature in quaternary palynology. Review of Palaeobotany and Palynology, 122 ( 1-2): 29 - 45.
Kingma, D. P. and Ba, J. ( 2014). Adam: A method for stochastic optimization. arXiv preprint arXiv: 6980.
Nakagawa, T., Edouard, J.-L., and de Beaulieu, J.- L. ( 2000). A scanning electron microscopy (sem) study of sediments from lake cristol, southern french alps, with special reference to the identification of pinus cembra and other alpine pinus species based on sem pollen morphology. Review of Palaeobotany and Palynology, 108 (1-2): 1 - DOI: 10.1016/s0034-6667(99)00030-5
Ng, A. ( 2019). Machine learning yearning: Technical strategy for ai engineers in the era of deep learning. Technical report, Tech. Rep.
Prince, S. J. ( 2012). Computer vision: models, learning, and inference. Cambridge University Press. DOI: 10.1017/cbo9780511996504
Quinta, L. N. B. ( 2013). Visao computacional aplicada na classificacção de graos de pólen. Master's thesis, Programa de Pó s Graduação em Biotecnologia, Universidade Católica Dom Bosco.
Quinta, L. N. B., Amorim, W. P., de Carvalho, M. H., Cereda, M. P., and Pistori, H. ( 2012). Floresta de caminhos ótimos na classificação de pólen. In Workshop de Visão Computacional.
Russakovsky, O., Deng, J., Su, H., Krause, J., Satheesh, S., Ma, S., Huang, Z., Karpathy, A., Khosla, A., Bernstein, M., et al. ( 2015). Imagenet large scale visual recognition challenge. International journal of computer vision, 115 ( 3): 211 - 252. DOI: 10.1007/s11263-015-0816-y
Von Der Ohe, W., Oddo, L., Piana, M., Morlot, M., and Martin, P. ( 2004). Harmonized methods of melissopalynology. 35 : 18 - 25. DOI: 10.1051/apido:2004050
Publicado
09/09/2019
Como Citar
ARISTIMUNHA, Bruno; BORGES, Felipe Silveira Brito; GONÇALVES, Ariadne Barbosa; PISTORI, Hemerson.
A Comparison Study of Deep Convolutional Neural Networks for the Classification of Brazilian Savannah Pollen Grains: Preliminary Results. In: WORKSHOP DE VISÃO COMPUTACIONAL (WVC), 15. , 2019, São Bernardo do Campo.
Anais [...].
Porto Alegre: Sociedade Brasileira de Computação,
2019
.
p. 91-96.
DOI: https://doi.org/10.5753/wvc.2019.7634.
