Automatic thresholding of infected blood images using granulometry and regional extrema

Author

Ruberto, Cecilia Di ; Dempster, Andrew ; Khan, Shahid ; Jarra, Bill

Author_Institution

Dept. of Math., Cagliari Univ., Italy

Volume

3

fYear

2000

fDate

2000

Firstpage

441

Abstract

This work introduces a morphological method for detecting malaria parasites in images of Giemsa stained blood slides. Generally, blood images are made up of three different kinds of cells: red, white and blood platelets. These are distinguished by their dimensions and their colour. In malarial blood the red corpuscles of vertebrates are infected by malaria parasites. The aim of our system is to detect the parasites by means of an automatic thresholding based on a morphological approach, using granulometries to evaluate the size of the red cells and the nuclei of parasites, and the regional maxima to mark the nuclei of parasites

Keywords

blood; image colour analysis; image recognition; mathematical morphology; medical image processing; Giemsa; automatic thresholding; granulometry; image recognition; infected blood images; malaria parasites; morphological method; Biomedical imaging; Cells (biology); Data mining; Diseases; Mathematics; Microscopy; Pixel; Red blood cells; Shape; Surface morphology;

fLanguage

English

Publisher

ieee

Conference_Titel

Pattern Recognition, 2000. Proceedings. 15th International Conference on

Conference_Location

Barcelona

ISSN

1051-4651

Print_ISBN

0-7695-0750-6

Type

conf

DOI

10.1109/ICPR.2000.903579

Filename

903579