A new approach to white blood cell nucleus segmentation based on gram-schmidt orthogonalization

S. H. Rezatofighi, H. Soltanian-Zadeh, R. Sharifian, R. A. Zoroofi

Research output: Chapter in Book/Report/Conference proceedingConference PaperResearchpeer-review

37 Citations (Scopus)

Abstract

The differential counting of white blood cells provides invaluable information to hematologist for diagnosis and treatment of many diseases. Manually counting of white blood cells is a tiresome, time-consuming and susceptible to error procedure. Due to the tedious nature of this process, an automatic system is preferable. In this automatic process, Segmentation of white blood cells is one of the most important stages. The nucleus of white blood cells has the most information about the type of white blood cells, thus an exact segmentation seems to be helpful for other stages of automatic recognition of white blood cells. In this paper, we introduced a novel method based on orthogonality theory and Gram-Schmidt process for segmenting the nuclei of white blood cells. For evaluation of results, we compared our proposed method with a hematologist manual segmentation. Results show robustness of this technique for segmentation of nuclei, while this method is very simple to implement.

Original languageEnglish
Title of host publicationProceedings - 2009 International Conference on Digital Image Processing, ICDIP 2009
PublisherIEEE, Institute of Electrical and Electronics Engineers
Pages107-111
Number of pages5
ISBN (Print)9780769535654
DOIs
Publication statusPublished - 4 Aug 2009
Externally publishedYes
EventInternational Conference on Digital Image Processing 2009 - Bangkok, Thailand
Duration: 7 Mar 20099 Mar 2009

Conference

ConferenceInternational Conference on Digital Image Processing 2009
CountryThailand
CityBangkok
Period7/03/099/03/09

Keywords

  • Gram-schmidt process
  • Hematological image
  • Nucleus segmentation
  • Orthogonality
  • White blood cell

Cite this