An Efficient Segmentation Method for Milk Somatic Cell Images

  • Heru Xue
  • Shuoshi Ma
  • Xichun Pei
Part of the The International Federation for Information Processing book series (IFIPAICT, volume 259)

The accurate segmentation of milk somatic cells in microscope images may contribute to development of a successful system that automatically analyzes, detects and counts cells in microscope images. We present a method for milk somatic cell Segmentation. Our approach is based on segmentation of subsets of bands using mathematical morphology followed by the fusion of the resulting segmentation “channels”. For color images, the band subsets are chosen as RG, RB and GB pairs. The segmentation in 2D color spaces is obtained using the watershed algorithm. These 2D segmentations are then combined to obtain a final result using a region split-and-merge process. Milk somatic cell images are segmented, and background, nucleus and cytoplasm can be extracted correctly. The most important feature of this method is the improved performance.

Keywords

milk somatic cell color image segmentation mathematical morphology image fusion 

References

  1. Cheng H D, Sun Y. A hierarchical approach to color image segmentation using homogeneity, IEEE Trans. On Image Processing, 2000, 9(12): 2071-2082.Google Scholar
  2. Comaniciu D, Meer P. Mean Shift Analysis and Applications, IEEE Int’l Conf. Comp. Vis., Kerkyra, Greece, 1999: 1197-1203.Google Scholar
  3. Géraud T, Strub P Y, Darbon J. Color image segmentation based on automatic morphological clustering, in Proc. IEEE International Conference on Image Processing, 2001: 70-73.Google Scholar
  4. Kurugollu F, Sankur B, Harmanci A E. Color image segmentation using histogram multithresholding and fusion, Journal of Image and Vision Computing, 2001, 19(13): 915-928.CrossRefGoogle Scholar
  5. Xue H, Pei X, Géraud T, Ma S. Color image segmentation using fuzzy sets and fusion, in Conference Proceedings of the Sixth International Conference on Electronic Measurement & Instruments (ICEMI’2003), 2003: 72-75.Google Scholar

Copyright information

© IFIP International Federation for Information Processing 2008

Authors and Affiliations

  • Heru Xue
    • 1
  • Shuoshi Ma
    • 1
  • Xichun Pei
    • 1
  1. 1.College of Computer and Information EngineeringInner Mongolia Agricultural UniversityChina

Personalised recommendations