Circular Hough Transform to improve viable Saccharomyces cerevisiae identification

• Felipe Silveira Brito Borges UNIDEB
• Diogo Soares da Silva UCDB
• Lia Nara Balta Quinta UFMS
• Arnaldo Ibanhe Mongelo UFMS
• Marney Pascoli Cereda UNESP
• Hemerson Pistori UCDB / UFMS

DOI: https://doi.org/10.5753/wvc.2021.18895

Abstract

Yeast counting is an important step in monitoring the fermentation process in sugarcane mills to optimize ethanol production. There is a need for a faster method to count viable cells in place of the fastidious and operator-dependent traditional method. In this paper, the application of a slightly modified version of the standard Circular Hough Transforms to automate the inoculated fermentation process of Saccharomyces cerevisae is reported. The results of several experiments with different preprocessing algorithms and parameter adjustments are presented. The resulting system will be part of a microbiological control procedure that is being developed to respond to Brazilian ethanol sugarcane mill's demands.

Keywords: Yeast detection, Hough transform, Machine Vision, Object Counting

References

E. Campelo and I. L. Michels, “A expansão da agroindústria canavieira em Mato Grosso do Sul,” Revista de Política Agrícola, no. 3, 2009.

S. et al, Balanço nacional de cana-de-a cúcar e agroenergia. Ministério da Agricultura , Pecuária e Abastecimento, Brasília, DF, 2007.

M. Sullivan and B. Bradford, “Viable cell yield from active dry yeast products and effects of storage temperature and diluent on yeast cell viability1,” Journal of Dairy Science, vol. 94, no. 1, pp. 526 - 531, 2011.

M. Atanasova, G. Yordanova, R. Nenkova, Y. Ivanov, T. Godjevargova, and D. Dinev, “Brewing yeast viability measured using a novel fluorescent dye and image cytometer,” Biotechnology & Biotechnological Equipment, vol. 33, no. 1, pp. 548-558, 2019.

N. Stolze, C. Bader, C. Henning, J. Mastin, A. E. Holmes, and A. L. Sutlief, “Automated image analysis with imagej of yeast colony forming units from cannabis flowers,” Journal of microbiological methods, vol. 164, p. 105681, 2019.

Q. Liang, J. Long, Y. Nan, G. Coppola, K. Zou, D. Zhang, and W. Sun, “Angle aided circle detection based on randomized hough transform and its application in welding spots detection,” Mathematical biosciences and engineering: MBE, vol. 16, no. 3, p. 1244, 2019.

G. Lin, Y. Tang, X. Zou, J. Cheng, and J. Xiong, “Fruit detection in natural environment using partial shape matching and probabilistic hough transform,” Precision Agriculture, pp. 1-18, 2019.

W. O. Barbosa and A. W. Vieira, “On the improvement of multiple circles detection from images using hough transform,” TEMA (São Carlos), vol. 20, no. 2, pp. 331-342, 2019.

H. M. Ünver, Y. Kökver, E. Duman, and O. A. Erdem, “Statistical edge detection and circular hough transform for optic disk localization,” Applied Sciences, vol. 9, no. 2, p. 350, 2019.

L. D. Novovic, V. S. Ostojic, D. S. Starvevic, and V. S. Petrovic, “Radiography calibration marker detection using hough transformation,” Telfor Journal, vol. 11, no. 1, pp. 30-34, 2019.

N. Stolze, C. Bader, C. Henning, J. Mastin, A. E. Holmes, and A. L. Sutlief, “Automated image analysis with imagej of yeast colony forming units from cannabis flowers,” Journal of Microbiological Methods, v.164, 2019.

R. O. Duda and P. E. Hart, “Use os the hough transformation to detect lines and curves in pictures,” Graphics and Image Processing, vol. 15, no. 01, 1972.

P. V. C. Hough, “Method and means for recognizing complex patterns,” USENIX Security Symposium, 1962.

P. Hull, Glucose Syrups: Technology and Applications. Wiley-Blackwell, March 2010.

A. Gosiewska, M. Bakala, K. Woznica, M. Zwolinski, and P. Biecek, “Epp: interpretable score of model predictive power,” arXiv preprint arXiv:1908.09213, 2019.

L. Gun, Z. Ran, and C. Honglei, “A contour detector with improved corner detection,” Multimedia Tools and Applications, vol. 76, no. 4, pp. 5965-5984, 2017.