A Segmentation Method for Counting Microbial Cells in Microscopic Image

  • Kim, Hak-Kyeong (Dept. of Mechanical Eng., College of Eng., Building 9, Pukyong National University) ;
  • Lee, Sun-Hee (Dept. of Microbiology, Building 7, Pukyong National University) ;
  • Lee, Myung-Suk (Dept. of Microbiology, Building 7, Pukyong National University) ;
  • Kim, Sang-Bong (Dept. of Mechanical Eng., College of Eng., Building 9, Pukyong National University)
  • Published : 2002.09.01

Abstract

In this paper, a counting algorithm hybridized with an adaptive automatic thresholding method based on Otsu's method and the algorithm that elongates markers obtained by the well-known watershed algorithm is proposed to enhance the exactness of the microcell counting in microscopic images. The proposed counting algorithm can be stated as follows. The transformed full image captured by CCD camera set up at microscope is divided into cropped images of m$\times$n blocks with an appropriate size. The thresholding value of the cropped image is obtained by Otsu's method and the image is transformed into binary image. The microbial cell images below prespecified pixels are regarded as noise and are removed in tile binary image. The smoothing procedure is done by the area opening and the morphological filter. Watershed algorithm and the elongating marker algorithm are applied. By repeating the above stated procedure for m$\times$n blocks, the m$\times$n segmented images are obtained. A superposed image with the size of 640$\times$480 pixels as same as original image is obtained from the m$\times$n segmented block images. By labeling the superposed image, the counting result on the image of microbial cells is achieved. To prove the effectiveness of the proposed mettled in counting the microbial cell on the image, we used Acinetobacter sp., a kind of ammonia-oxidizing bacteria, and compared the proposed method with the global Otsu's method the traditional watershed algorithm based on global thresholding value and human visual method. The result counted by the proposed method shows more approximated result to the human visual counting method than the result counted by any other method.

References

  1. Image Processing Analysis, and Machine Vision M. Sonaka;V. Hlavac;R. Boyle
  2. Biotechnology and Bioengineering v.60 no.1 In-situ microscopy for on-line determination of biomass C. Bittner. G;Wehnert;T. Scheper https://doi.org/10.1002/(SICI)1097-0290(19981005)60:1<24::AID-BIT3>3.0.CO;2-2
  3. Institute of Electrical and Electronics Engineers(IEEE) Transaction on Image Processing v.7 no.6 A recursive thresholding technique for image segmentation M. Cheriet;J. N. Said;C. Y. Suen
  4. Journal of the Korean Fisheries Society v.31 Isolation of ammonia oxidizing bacteria and their characteristics M. S. Lee;J. H. Park
  5. IEEE Pacific Rim Conference on Communications, Computers, and Signal Processing Image thresholding techniques Mahboob H. Chowdhury;Warren D. Little
  6. IEEE Transaction on Pattern Analysis and Machine Intelligence v.13 no.6 Watershed in digital spaces: An efficient algorithm based on immersion simulations L. Vincent;P. Soille https://doi.org/10.1109/34.87344
  7. The international Society for Optical Engineering(SPIE) Visual Communication Image Processing v.1818 no.2 Morphological multiscale segmentation of images P. Salembia;J. Serra
  8. International Conference on Circuits and Systems v.1 Automatic thresholding of gray-level pictures using two-dimensional Ostu method J. Liu;W. Li;Y. Tien
  9. Journal of Microscopy v.58 Study of the early growth and branching of Streptomyces tendae by means of an image processing system U. Reichl;T. Buschulte;E. Gilles
  10. IEEE transaction on systems, man and cybernetics v.SMC-9 A thresholding selection method from gray-level histogram N. Otsu
  11. International Workshop on Image Processing: Real-time edge and motion detection/estimation Use of watershed in contour detection S. Beucher;C. Lantuejoul