Abstract
In this paper, we propose an asbestos detection method focusing on frequency distribution of microscopic images. In building construction, asbestos has been used for molding plates and heat insulation materials. However, increased injury caused by asbestos has become a problem in Japan. Removal of asbestos from building materials and rendering it harmless are common means of alleviating asbestos hazards. Nevertheless, those processes necessitate a judgment of whether asbestos is included in building materials. According to the JIS standards, it is necessary to count 3000 particles in microscopic images. We consider the asbestos shape, and define a new feature obtained through frequency analysis. The proposed method intensifies the low-brightness asbestos using its feature, so it can detect not only high-brightness particles and asbestos but also low-brightness asbestos. We underscore the effectiveness of the method by comparing its results with results counted by an expert.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Walter, C.: Detection and identification of asbestos by microscopical dispersion staining. Environmental Health Perspectives 9, 57–61 (1974)
JIS (Japanese Industrial Standard) A 1481: Determination of asbestos in building material products (2006)
Kawabata, K., Morishita, S., Takemura, H., Hotta, K., Mishima, T., Asama, H., Mizoguchi, H., Takahashi, H.: Development of an automated microscope for supporting qualitative asbestos analysis by dispersion staining. Journal of Robotics and Mechatronics 21, 186–192 (2009)
Baron, P.A., Shulman, S.A.: Evaluation of the magiscan image analyzer for asbestos fiber counting. American Industrial Hygiene Association Journal 48, 39–46 (1987)
Kenny, L.C.: Asbestos fibre counting by image analysis - the performance of the manchester asbestos program on magiscan. Annals of Occupational Hygiene 28, 401–415 (1984)
Inoue, Y., Kaga, A., Yamaguchi, K.: Development of an automatic system for counting asbestos fibers using image processing. Particulate Science and Technology 16, 263–279 (1998)
Shen, L., Song, X., Iguchi, M., Yamamoto, F.: A method for recognizing particles in overlapped particle images. Pattern Recognition Letters 21, 21–30 (2000)
Stokes, M.D., Deane, G.B.: A new optical instrument for the study of bubbles at high voidfractions within breaking waves. IEEE Journal of Oceanic Engineering 24, 300–311 (1999)
Duraiswami, R., Prabhukumar, S., Chahine, G.L.: Bubble counting using an inverse acoustic scattering method. The Journal of the Acoustical Society of America 104, 2699–2717 (1998)
Berzins, V.: Accuracy of laplacian edge detectors. Computer Vision, Graphics, and Image Processing 27, 195–210 (1984)
Canny, J.: A computational approach to edge detection. IEEE Transactions on Pattern Analysis and Machine Intelligence 8, 679–698 (1986)
Marr, D., Hildredth, E.: Theory or edge detection. Proceedings of the Royal Society London 207, 187–217 (1980)
Kumagai, H., Morishita, S., Kawabata, K., Asama, H., Mishima, T.: Accuracy improvement of counting asbestos in particles using a noise redacted background subtraction. In: IEEE International Conference on Multisensor Fusion and Integration for Intelligent Systems, pp. 74–79 (2008)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2009 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Kumagai, H., Morishita, S., Kawabata, K., Asama, H., Mishima, T. (2009). Asbestos Detection Method with Frequency Analysis for Microscope Images. In: Bebis, G., et al. Advances in Visual Computing. ISVC 2009. Lecture Notes in Computer Science, vol 5876. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-10520-3_40
Download citation
DOI: https://doi.org/10.1007/978-3-642-10520-3_40
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-10519-7
Online ISBN: 978-3-642-10520-3
eBook Packages: Computer ScienceComputer Science (R0)