Viable Yeast Identification using Bag of Visual Words in Colored images
Resumo
In this research it is reported a system to automate the process of identification of viable yeasts whose population control is a crucial task in the ethanol production process. The identification and counting of yeasts made by human vision under a light microscope, is repetitive and susceptible to errors. We used computer vision techniques such as BoVW, Color Coherence Vectors (CCV), Color Moments (CM), Bag-of-Color (BoC) and Opponent Color (OpC) were applied for extracting characteristics that were classified by the Naive Bayes, KNN, SVM and J48 algorithms in 2614 images of yeasts separated into three classes: viable, non-viable and background. The results were analyzed using software R, which in the ANOVA test resulted in a p value equal to 2e16 indicating a significant difference between the techniques. The OPC with SVM classifier showed the highest performance using the PCC Percent Correct Classification metric, about 95% compared to other techniques.
Referências
Boinot, M. 1939. Process of alcoholic fermentation with re-use os the yeass. The internatioal Sugar Journal.
Stratford, M., 1996. Yeast occulation: restructuring the theories in line with recent research. Belgian J. Brew. Biotechnol.
Ceccato-Antonini, S.R., 2011. Microbiologia da fermentao alcolica: a importância do monitoramento microbiolgico em destilarias. So Carlos: Universidade Federal de So Carlos, p. 105.
Van Weijer, J., Khan, F. S. 2013. Fusing color and shape for bag- of-words based object recognition. In Computational Color Imaging, Springer, p. 2534.
Pass, G., Zabih, R., Miller, J., 1997. Comparing images using color coherence vectors, in: Proceedings of the Fourth ACM International Conference on Multimedia. p. 6573.
Bahri, A., Zouaki, H., 2013. A SURF-color moments for images retrieval based on bag-of features. Eur. J. Comput. Sci. Inf. Technol. 1, 1122.
Wengert, C., Douze, M., Jgou, H., 2011. Bag-of-colors for improved image search, in: Proceedings of the 19th ACM International Conference on Multimedia. p. 14371440.
van de Sande, K.E.A., Gevers, T., Snoek, C.G.M., 2008. Color descriptors for object category recognition, in: Conference on Colour in Graphics, Imaging, and Vision. p. 378381.
Chan, L.L., Lyette, E.J., Pirani, A., Smith, T., Qiu, J., Lin, B., 2011. Direct concentration and viability measurement of yeast in corn mash using a novel imaging cytometry method. J. Ind. Microbiol. Biotechnol. 38, p. 11091115. doi: 10.1007/s10295-010-0890-7.
Zhang, T., Fang, H.H.P., 2004. Quantication of Saccharomyces cerevisiae viability using BacLight. Biotechnol. Lett. 26, 989992.
Chan, L.L., Kury, A., Wilkinson, A., Berkes, C., Pirani, A., 2012. Novel image cytometric method for detection of physiological and metabolic changes in Saccharomyces cerevisiae. J. Ind. Microbiol. Biotechnol. 39, p. 16151623. doi: 10.1007/s10295-012-1177-y.
Saldi, S., Driscoll, D., Kuksin, D., Chan, L.L.-Y., 2014. Image-based cytometric analysis of uorescent viability and vitality staining methods for ale and lager fermentation yeast. J. Am. Soc. Brew. Chem. 72, 253260. doi: https://doi.org/10.1094/ASBCJ-2014-1015-01.
Versari, C., Stoma, S., Batmanov, K., Llamosi, A., Mroz, F., Kacz- marek, A., Deyell, M., Lhoussaine, C., Hersen, P., Batt, G., 2017. Long-term tracking of budding yeast cells in brighteld microscopy: CellStar and the Evaluation Platform. J. R. Soc. Interface 14. doi: 10.1098/rsif.2016.0705.
Feizi, A., Zhang, Y., Greenbaum, A., Guziak, A., Luong, M., Chan, R., Berg, B., Ozkan, H., Luo, W., Wu, M., others, 2017a. Lensfree on- chip microscopy achieves accurate measurement of yeast cell viability and concentration using machine learning, in: CLEO: Applications and Technology. p. ATh4B–4.
Feizi, A., Zhang, Y., Greenbaum, A., Guziak, A., Luong, M., Chan, R.Y.L., Berg, B., Ozkan, H., Luo, W., Wu, M., others, 2017b. Yeast viability and concentration analysis using lens-free computational microscopy and machine learning, in: Optics and Biophotonics in Low- Resource Settings III. p. 1005508.
Hong, D., Lee, G., Jung, N.C., Jeon, M., 2013. Fast automated yeast cell counting algorithm using bright-eld and uorescence microscopic images. Biol. Proced. Online 15, 13. doi: 10.1186/1480-9222-15-13.
Wei, N., Flaschel, E., Friehs, K., Nattkemper, T.W., 2008. A machine vision system for automated non-invasive assessment of cell viability via dark eld microscopy, wavelet feature selection and classication. BMC Bioinformatics 9, 449. doi: 10.1186/1471-2105-9-449.
Yu, B.Y., Elbuken, C., Ren, C.L., Huissoon, J.P., 2011. Image processing and classication algorithm for yeast cell morphology in a microuidic chip. J. Biomed. Opt. 16, 66008. doi: 10.1117/1.3589100.
Yu, B.Y., Elbuken, C., Shen, C., Huissoon, J.P., Ren, C.L., 2018. An integrated microuidic device for the sorting of yeast cells using image processing. Sci. Rep. 8, 3550. doi:10.1038/s41598-018-21833-9.
Mas, S., Ghommidh, C., 2001. On-line size measurement of yeast aggregates using image analysis. Biotechnol. Bioeng. 76, p. 9198. doi: 10.1002/bit.1148.
Mongelo, A.I., Da Silva, D.S., Quinta, L.I.A.N.B., Pistoti, H., Cereda, M.P., 2011. Validação de método baseado em visão computacional para automação de contagem de viabilidade de leveduras em indústrias alcooleiras, in: VIII Congresso Brasileiro de Agroinformática SBIAGRO.