Applying Convolutional Neural Networks in Images for Automated Recognition of Honey Bees (Apis mellifera L.)

• Caio Martim Barros UFC http://orcid.org/0000-0002-0694-4542
• Emannuel Diego Gonçalves de Freitas IFCE http://orcid.org/0000-0003-4820-3459
• Antonio Rafael Braga UFC https://orcid.org/0000-0001-9105-9056
• Isac Gabriel Abrahão Bomfim IF Sertão PE https://orcid.org/0000-0001-5813-1896
• Danielo G. Gomes UFC https://orcid.org/0000-0002-8285-4629

DOI: https://doi.org/10.5753/wcama.2021.15733

Abstract

The recognition of bee species and other pollinators can directly contribute to the conservation of ecosystems. The objective of this work is to develop a model of digital image processing, for automatic recognition of honey bees (Apis mellifera L.) among the other bee species and other insects, through the use of convolutional neural networks. For training the proposed model, a data set consisting of 2.300 images was used, separated between the species of honey bee and other insects (including other bees in this class), which were called "Non Apis". The proposed neural network model returned answers with 94% accuracy, culminating in a prediction model with a high precision index capable of recognize images of the same species of bee (A. mellifera) and differentiating it from other bees and other insects species.

Keywords: Apis mellifera L, Digital Image Processing, Classification, CNN

References

Bomfim, I. G. A., Freitas, B. M., de Aragão, F. A. S., Walters, S. A., and Pessarakli, M. (2016). Pollination in cucurbit crops. Handbook of Cucurbits: Growth, Cultural Practices, and Physiology. Florida (US): CRC Press. https://doi.org/10.1201/b19233-16.

Buschbacher, K., Ahrens, D., Espeland, M., and Steinhage, V. (2020). Image-based species identification of wild bees using convolutional neural networks. Ecological Informatics, 55:37–45.

Fagundes, J. M. G., Rebelo, A. R., Digiampietri, L. A., and Bíscaro, H. H. (2020). Fully automatic segmentation of bee wing images. Revista Brasileira de Computação Aplicada, 12 (2):37–45.

Freitas, B. M. and Bomfim, I. G. A. (2017). A necessidade de uma convivência harmônica da agricultura com os polinizadores. Importância dos polinizadores na produção de alimentos e na segurança alimentar global. Brasília, DF: Centro de Gestão e Estudos Estratégicos.

Freitas, D., Camargo, S., Comin, H., Domingues, R., Gaspar, E., and Cardoso, F. (2019). Reconhecimento da ceratoconjuntivite infecciosa bovina utilizando imagens termográficas e redes neurais convolucionais. Revista Brasileira de Computação Aplicada, 11(3):133–145.

Gao, D., Sun, Q., Hu, B., and Zhang, S. (2020). A framework for agricultural pest and disease monitoring based on internet-of-things and unmanned aerial vehicles. Sensors, 20(5):1487.

Gonzalez, R. C. and Woods, R. E. (2011). Digital Image Processing. Pearson Prentice Hall, 3th edition.

Iost Filho, F. H., Heldens, W. B., Kong, Z., and de Lange, E. S. (2020). Drones: Innovative technology for use in precision pest management. Journal of economic entomology, 113(1):1–25.

Kasinathan, T., Singaraju, D., and Uyyala, S. R. (2020). Insect classification and detection in field crops using modern machine learning techniques. Information Processing in Agriculture.

Liu, S., Shih, F. Y., Russell, G., Russell, K., and Phan, H. (2020). Classification of ecological data by deep learning. International Journal of Pattern Recognition and Articial Intelligence, 34 (13):37 – 45.

Mason, L., Kondratieff, B. C., and Seshadri, A. (2018). Native Bee Watch: A Colorado Citizen Science Field Guide. Colorado State University, College of Agricultural Sciences

Milfont, M. d. O., Rocha, E. E. M., Lima, A. O. N., and Freitas, B. M. (2013). Higher soybean production using honeybee and wild pollinators, a sustainable alternative to pesticides and autopollination. Environmental chemistry letters, 11(4):335–341.

Monteiro, A. A. d. O. et al. (2019). Segmentação e identificação de cultivo e espécies invasivas em imagens aéreas utilizando redes neurais convolucionais.

Morais, M. M., De Jong, D., Massage, D., and Gonçalves, L. S. (2012). Perspectivas e desafios para o uso das abelhas apis mellifera como polinizadores no brasil. Polinizadores no Brasil. Edusp, São Paulo, Brasil.

Potts, S. G., Imperatriz-Fonseca, V., Ngo, H., Biesmeijer, J. C., Breeze, T., Dicks, L., Garibaldi, L., Settele, J., Vanbergen, A. J., Aizen, M. A., et al. (2016). Summary for policymakers of the assessment report of the intergovernmental science-policy platform on biodiversity and ecosystem services (ipbes) on pollinators, pollination and food production. Technical report.

Rey, G. (2020). The bee or wasp? dataset: 19480 hand curated photos of bees, wasps and other insects. https://www.kaggle.com/jerzydziewierz/bee-vs-wasp. Accessed: 2021-04-12.

Roskov, Y., Kunze, T., Paglinawan, L., Orrell, T., Nicolson, D., Culham, A., Bailly, N., Kirk, P., Bourgoin, T., Baillargeon, G., et al. (2013). Species 2000 & itis catalogue of life, 2013 annual checklist.

Schurischuster, S. and Kampel, M. (2020). Image-based classification of honeybees. In 2020 Tenth International Conference on Image Processing Theory, Tools and Applications (IPTA), pages 1–6.

Sledevic, T. (2018). The application of convolutional neural network for pollen bearing bee classification. In 2018 IEEE 6th Workshop on Advances in Information, Electronic and Electrical Engineering (AIEEE), pages 1–4.

Tian, H., Wang, T., Liu, Y., Qiao, X., and Li, Y. (2020). Computer vision technology in agricultural automation —a review. Information Processing in Agriculture, 7(1):1–19.

Tuda, M. and Luna-Maldonado, A. I. (2020). Image-based insect species and gender classification by trained supervised machine learning algorithms. Ecological Informatics, 60:101135.

Yang, J. (2019). The beeimage dataset: Annotated honey bee images. https://www.kaggle.com/jenny18/honey-bee-annotate-images. Accessed: 2021-02-20.