PARAMETERS OF FILTERING BY LOG FILTER OF MICROSCOPIC IMAGES OF SPUTUM STAINED BY ZIEHL – NEELSEN METHOD
DOI:
https://doi.org/10.18413/2687-0932-2020-47-2-362-371Keywords:
image processing, tuberculosis bacteria, microscopic, method Ziehl – Nielsen, Laplacian, LOG filter, high-frequency filtering, normalized color difference, NCDAbstract
Mycobacterium tuberculosis infection remains a major public health issue of global morbidity and mortality. One of the widely used methods for the finding of mycobacterium tuberculosis is the Ziehl-Nielsen method of microscopy. In this paper a method for removing noise without producing image distortion for Ziehl-Neelsen stained images of sputum smear samples obtained using a light microscope is presented. The proposed approach is based on the convolution of the original image with the Laplacian of a Gaussian filter enhanced by high-frequency filtering. Used Laplacian of Gaussian filter was discretized as a 9x9 convolution kernel. If the original image is filtered with a simple Laplacian of Gaussian, the resulting output is rather noisy. Combining this result of filtration with the enhanced by high-frequency filtering will reduce the noise and will keep of mycobacterium tuberculosis for further analysis by automated medical diagnostic systems. In order to deal with automatic determination of filtering quality the normalized color difference was proposed. Such measure is evaluated in CIE Luv color spaces in order to appraise the filtration quality of a filtered picture at the human expert examination level.
Downloads
References
Глобальный доклад о туберкулезе ВОЗ за 2019 год. URL: http://www.who.int/tb/publications/ global_report/ru/ (дата обращения: 20 марта 2020).
Гонсалес Р., Вудс Р. 2005. Цифровая обработка изображений. М., Техносфера, 1072. 3. Минздрав России. 2003. О совершенствовании противотуберкулезных мероприятий в Российской Федерации. Приказ. М., 2003, 109.
Наркевич А.Н., Шеломенцева И.Г., Виноградов К.А., Сысоев С.А. 2017. Сравнение методов сегментации цифровых микроскопических изображений мокроты, окрашенных по методу Циля –Нильсена. Инженерный вестник Дона. 4: 1–11.
Наркевич А.Н. 2017. Алгоритмы сегментации цифровых микроскопических изображений мокроты, окрашенной по методу Циля – Нильсена. World Science Proceedings of articles the international scientific conference (Карловы Вары – Москва, 28–29 января 2017). М, МЦНИП: 431–436.
Наркевич А.Н., Виноградов К.А., Корецкая Н.М., Соболева В.О. 2017. Сегментация микроскопических изображений мокроты, окрашенной по методу Циля – Нильсена, с использованием вейвлет-преобразования Mexican Hat. Acta Biomedica Scientifica. Том 2. 5 (1): 141–146.
Прэтт У. 1982. Цифровая обработка изображений. Кн.2. М., Мир, 480.
Севастьянова Э.В. 2009. Совершенствование микробиологической диагностики туберкулеза в учреждениях противотуберкулезной службы и общей лечебной сети: дисc. …д-ра биол. наук. Москва, 395.
Шеломенцева И.Г. 2017. Результаты фильтрации и сегментации изображений анализа мокроты, окрашенной по методу Циля – Нильсена. International journal of advanced studies. 7 (4–2): 110–114.
Bhairannawar, S.S., Patil, A.N., Janmane, A.S., Huilgol, M.V. 2017. Color image enhancement using Laplacian filter and contrast limited adaptive histogram equalization. Innovations in Power and Advanced Computing Technologies (i-PACT): 1–5.
Dey N., Ashour A.S., Shi F., Balas V.E. 2018. Soft Computing Based Medical Image Analysis. Academic Press, 292.
Gonzalez R.C., Woods R.E., Eddins S.L. 2009. Digital Image Processing using Matlab. Gatesmark Publishing, 827.
Millan M.S., Valencia E. 2004. Laplacian filter based on color difference for image enhancement. Proceedings of SPIE - The International Society for Optical Engineering: 1259–1264.
Morton K.W., Mayers D.F. 2005. Numerical solution of partial differential equations. Cambridge University Press, 385.
Ponomarenko N., Battisti F., Egiazarian K., Astola J., Lukin V. 2009. Metrics performance comparison for color image data-base. In: Proceedings of the 4th International Workshop on VideoProcessing and Quality Metrics for Consumer Electronics (Scotts-dale, Arizona, USA, 14–16 January, 2009). 1–6.
Russo F. 2013. Accurate tools for analyzing the behavior of impulse noise reduction filters in color images. Journal of Signal and Information Processing, Scientific Research Publishing. 4: 42–50.
Russo F. 2014. Performance Evaluation of Noise Reduction Filters for Color Images through Normalized Color Difference (NCD) Decomposition. IRSN Machine Vision: 1–11.
Sunada T. 2008. Discrete geometric analysis. Proceedings of Symposia in Pure Mathematics. 77: 51–86.
Szeliski R. 2010. Computer Vision: Algorithms and Applications. Springer, 957.
Wang R. 2012. Introduction to Orthogonal Transforms. With Applications in Data Processing and Analysis. Cambridge University Press, 528.
Abstract views: 648
