DocumentCode
2115169
Title
A Kind Of Cell Tracking Algorithm Based on Relaxation Iterative Segmentation Algorithm
Author
Lan, Gan ; Fei-hu, Zheng
Author_Institution
Sch. of Inf. Eng., East China Jiaotong Univ., Nanchang
fYear
2008
fDate
18-18 Dec. 2008
Firstpage
385
Lastpage
388
Abstract
A boundary tracking algorithm with two-dimensional chain tables was proposed to find out the cell nucleus in cytoplasm of the same cell, in which firstly the relaxation iterative algorithm was used in the automatical cell segmentation of the cell nucleus and cytoplasm. As a result of the relaxation iterative cell segmentation, the cell nucleus and cytoplasm were separated from the background clearly, which made a good foundation for the cell boundary tracking. Then a 4-neighbour boundary tracking algorithm was used to get the two-dimensional chain tables of nuclear and cytoplasm, which based on external normal preferential algorithm. Finally, line scan algorithm was used in the scanning of the pixels of cytoplasm parallel so that the cell nucleus in cytoplasm of the same cell was found out, which was innovational and useful for the cell recognition. And at last some test results was presented to show the effectiveness of the proposed algorithm.
Keywords
cellular biophysics; image segmentation; iterative methods; medical image processing; automatical cell segmentation; cell boundary tracking; cell nucleus; cell recognition; cell tracking algorithm; cytoplasm; line scan algorithm; relaxation iterative segmentation algorithm; two-dimensional chain; Adhesives; Biomedical engineering; Clustering algorithms; Eigenvalues and eigenfunctions; Gallium nitride; Image segmentation; Iterative algorithms; Microscopy; Seminars; Testing; boundary tracking; cell segmentation; chain table; nuclear; relaxation iterative;
fLanguage
English
Publisher
ieee
Conference_Titel
Future BioMedical Information Engineering, 2008. FBIE '08. International Seminar on
Conference_Location
Wuhan, Hubei
Print_ISBN
978-0-7695-3561-6
Type
conf
DOI
10.1109/FBIE.2008.61
Filename
5076763
Link To Document