Journal of the Korea Institute of Information and Communication Engineering (한국정보통신학회논문지)

The Korea Institute of Information and Commucation Engineering (한국정보통신학회)
권호 표지
DOI QR코드

DOI QR Code

An Efficient Segmentation System for Cell Images By Classifying Distributions of Histogram

히스토그램 분포 분류를 통한 효율적인 세포 이미지 분할 시스템

  • Cho, Migyung (Department of Media Engineering, Tongmyong University)
  • Received : 2013.10.15
  • Accepted : 2013.11.25
  • Published : 2014.02.28
Download PDF
⟨ Previous Next ⟩

Abstract

Cell segmentation which extracts cell objects from background is one of basic works in bio-imaging which analyze cell images acquired from live cells in cell culture. In the case of clear images, they have a bi-modal histogram distribution and segmentation of them can easily be performed by global threshold algorithm such as Otsu algorithm. But In the case of degraded images, it is difficult to get exact segmentation results. In this paper, we developed a cell segmentation system that it classify input images by the type of their histogram distribution and then apply a proper segmentation algorithm. If it has a bi-modal distribution, a global threshold algorithm is applied for segmentation. Otherwise it has a uni-modal distribution, our algorithm is performed. By experimentation, our system gave exact segmentation results for uni-modal cell images as well as bi-modal cell images.

세포 분할 작업은 세포 이미지의 배경으로부터 세포 영역을 추출하는 작업으로 배양과정에 있는 살아있는 세포를 이미지화하여 분석하는 바이오 이미징 분야에서 기초적인 작업들 중 하나이다. 선명한 이미지의 경우 바이모덜 히스토그램 분포를 가지므로 Otsu와 같은 전역임계값 알고리즘을 이용하여 쉽게 세포분할 작업을 수행할 수 있지만 희미한 이미지의 경우는 정확한 세포 분할을 하기가 어렵다. 본 논문에서는 입력된 세포이미지의 히스토그램을 분석하여 히스토그램 분포에 따라 분류한 후 바이모덜 분포를 가지는 이미지의 경우 전역임계값 알고리즘을 적용하고 유니모덜 분포를 가지는 이미지의 경우 영역을 분할하여 부분 영역별로 다른 임계값을 적용하는 새포 분할 시스템을 개발하였다. 실험결과 제안한 시스템은 바이모덜 분포를 가지는 세포이미지 뿐만 아니라 유니모덜 분포를 가지는 세포 이미지에 대해서도 정확한 세포 분할 작업을 수행하였다.

Keywords

References

  1. Xian Du, Sumeet Dua, "Segmentation of Fluorescence Microscopy Cell Image Using Unsupervised Mining," The Open Medical Information Journal, Vol.4, pp.41-49, 2010. https://doi.org/10.2174/1874431101004010041
  2. Migyung Cho, "An Algorithm for Determining Histogram Type of a Cell Image Using Polygonal Approximation," International Journal of Advancements in Computing Technology, Vol.5 No.13, pp.229-234, Sept., 2013.
  3. Thouis R. Jones, Anne Carpenter, Polina Golland, "Voronoibased segmentation of cells on image manifolds", Lecture Notes of Computer Science, Vol. 3765, pp 535-543, 2005.
  4. Bazi Y, Rruzzone L, Melgani F., "Image thresholding based on the EM algorithm and the generalized Gaussian distribution", Pattern Recognition Letter, Vol. 40, pp.619-634, 2007. https://doi.org/10.1016/j.patcog.2006.05.006
  5. P.K Sahoo, S. Soltani, A.K.C Wong, "A survey of thresholding techniques", Computer Vision, Graphics, and Image Processing, Vol. 41, Issue 2, pp. 233-260, 1988. https://doi.org/10.1016/0734-189X(88)90022-9
  6. Nobuyuki Otsu, "A threshold Selection Method from Gray-Level Histograms", IEEE Transactions on Systems, Man, and Cybernetics, Vol. SMC-9, No. 1, pp62-66, Jan., 1979.
  7. Migyung Cho and Jaesool Shim "Segmentation Algorithm of Fluorescence Microscopy Cell Images using Area Partition," in Proceeding of the 3rd International Conference on Convergence Technology 2013, Chiang Mai, Thailand, pp. 402-403, 2013.
  8. Feixianng Yan, Hong Zhang, C. Ronald Kube, "A multistage adaptive thresholding method," Pattern Recognition Letters, vol. 26, pp. 1183-1191, Dec. 2005. https://doi.org/10.1016/j.patrec.2004.11.003
  9. Nicolas Coudray, Jean-Luc Buessler, Jean-Philippe Urban, "Robust threshold estimation for images with unimodal histograms," Pattern Recognition Letters, vol. 31, pp. 1010-1019, Jan. 2010. https://doi.org/10.1016/j.patrec.2009.12.025