Automated Detection and Classification of the Diatom Microscopic Photo Images

Main Article Content

Maryna Viktorivna Ivanova
https://orcid.org/0000-0002-2686-6633
Yurii Volodymyrovych Vuntesmeri
https://orcid.org/0000-0002-0513-0205
Liudmyla Mykolaivna Bukhtiiarova
https://orcid.org/0000-0002-3427-6553

Abstract

The diatoms (Bacillariophyta) are a species-rich and extremely widespread microalgae. Many diatom species require a fairly narrow range of ecological conditions (temperature, pH, salinity, saprobity, trophic level of the water etc.). They are very sensitive to changes of different water chemical parameters that allows to use of the diatoms as the indicators in monitoring of water quality as well as for the ecological reconstruction using bottom sediments. Different methods of the diatom analysis are based on the species composition and species amount in the preparations of plankton, benthos and epyphyton. However this analysis requires highly qualified staff and the manual processing of hundreds samples. The development of the computer tools for the automatic diatom species detection and identification is an actual task to improve the effectiveness of ecological studies and simplify the time-consuming routine work of the researchers. The image processing methods were investigated for the diatom species automatic identification in the light microscopic photos of the samples that were collected for the routine monitoring. The methods of segmentation of the images based on the threshold processing and morphological differentiation of the images were studied. The two-steps segmentation of the diatom photos was proposed. The method of artificially expanding the training dataset by sequential image transformation was applied. Based on the prepared training dataset, two realizations of convolutional neural networks were trained and their accuracy evaluated.

Article Details

How to Cite
[1]
M. V. Ivanova, Y. V. Vuntesmeri, and L. M. Bukhtiiarova, “Automated Detection and Classification of the Diatom Microscopic Photo Images”, Мікросист., Електрон. та Акуст., vol. 24, no. 5, pp. 18–25, Oct. 2019.
Section
Electronic Systems and Signals
Author Biography

Liudmyla Mykolaivna Bukhtiiarova, State Institution "Institute of Evolutionary Ecology of NAS of Ukraine"

Лабораторія охорони та відтворення біорізноманіття,

References

Bukhtiyarova L. N. “Bacillariophyta v biomonitoringe rechnykh ekosistem. Covremennoye sostoyaniye i perspektivy ispol'-zovaniya [Bacillariophyta in the biomonitoring of river ecosystems. Current state and prospects of use]”, Al'gologiya, vol. 9, no. 3, pp. 89–103, 1999.

Bukhtiyarova L. N. “Classification of diatom algocoenoses as a useful tool in river biomonitoring. In: J. Prygiel, B. A. Whitton, J. Bukowska (eds) Use of algae for Monitoring Rivers. III”. – Agence de l'Eau Artois-Picardie, p. 114–121, 1999. URL: https://www.researchgate.net/publication/282974818_Classification_of_diatom_algocoenoses_as_a_useful_tool_in_river_biomonitoring

Treguer R., Nelson D. M., Van Bennkom A. J. “The silica balance in the world ocean: a reestimate”, Science, vol. 268, p. 375–379, 1995. URL: https://www.researchgate.net/ publication/6092964_The_Silica_Balance_in_the_World_Ocean_A_Reestimate

The European Parliament and the Council of the European Union. Directive 2000/60/EC. Establishing a Framework for Community Action in the Field of Water Policy; Official Journal of the European Community: Maastricht, the Netherlands, Work Safety Introduction, 2000. URL: https://injuryfacts.nsc.org/work/work-overview/work-safety-introduction/.

Lobo E., Heinrich C., Schuch M., Wetzel C., Ector L. “Diatoms as Bioindicators in Rivers”, River Algae, vol. 06, p. 245–271, 2016. https://doi.org/10.1007/978-3-319-31984-1_11

Wang Yi-K., Stevenson R., Sweets R., DiFranco J. “Developing and testing diatom indicators for wetlands in the Casco Bay watershed, Maine, USA” Hydrobiologia, vol. 561, no. 191, p. 245–271. 2006. DOI: 10.1007/s10750-005-1614-2

Stevenson R., Pan Y., Van Dam H. “Assessing environmental conditions in rivers and streams with diatoms”. In: Smol J. P. and Stoermer E. F. (Eds.) – The Diatoms: Applications for the Environmental and Earth Sciences. Cambridge, UK, Cambridge University Press, p. 57–85, 2010. DOI: 10.1017/CBO9780511763175.005.

Mayama S., Katoh K., Omori H., Seino S., Osaki H., Julius M., Lee J. H., Cheong C., Lobo E. A., Witkowski A., Srivibool R., Muangphra P., Jahn R., Kulikovskiy M., Hamilton P. B., Ya-Hui G., Ector L., Soeprobowat T. R. “Progress toward the Construction of an International Web-based Educational System Featuring an Improved "SimRiver" for the Understanding of River Environments”, Asian Journal of Biology Education, vol. 5, p. 2–14. 2011. URL: http://www.u-gakugei.ac.jp/~mayama/PDF/Mayama et al_2011_SimRiver_AJBE.pdf

Dimitrovski I., Kocev D., Loskovska S., Dzeroski S., “Hierarchical classification of diatom images using ensembles of predictive clustering trees”, Ecological Informatics, vol. 7, p. 19–29, 2012. URL: http://kt.ijs.si/DragiKocev/ECOINF/ECOINF_diatom_images.pdf

Bueno G., Deniz O., Pedraza A., Ruiz-Santaquiteria J., Salido J., Cristóbal G., Borrego-Ramos M., Blanco S., “Automated Diatom Classification (Part A): Handcrafted Feature Approaches,” Applied Sciences, vol. 7, no. 8, p. 753, 2017. URL: http://digital.csic.es/bitstream/10261/153574/1/applsci-07-00753.pdf

Pedraza A., Bueno G., Deniz O., Cristóbal G., Blanco S., Borrego-Ramos M. Automated Diatom Classification (Part B): A Deep Learning Approach, – Applied Sciences vol 7, p. 460, 2017. DOI: 10.3390/app7050460

Quantitative image analysis of microstructures. Exner H. E., Hougardy H. P. (Eds). DGM Informations‐gesellschaft Verlag, Oberursel, 235 pp., 1988. ISBN 3‐88355‐132‐5 DOI: 10.1002/adma.19900020216

Glasbey C. A., Horgan G. W. “Image analysis for the biological sciences”, Wiley J., Sons, Inc. New York, NY, USA, 230 pp. 1995. ISBN: 0-471-93726-6 DOI: 10.1017/S0021859600088924

Zheng J., Zhang D., Huang K., Sun Y., Tang S., “Adaptive windowed range-constrained Otsu method using local information”, Journal of Electronic Imaging, vol. 25, p. 013034 , 2016, DOI: 10.1117/1.JEI.25.1.013034

Jung A. “Imgaug”, 2017. URL: https://github.com/aleju/imgaug.

Iandola F. N., Han S., Moskewicz M. W., Ashraf K., Dally W. J., Keutzer K. “SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and

Simonyan K., Zisserman A. “Very deep convolutional networks for large-scale image recognition”. arXiv preprint, 2014. arXiv: 1409.1556