A fuzzy approach to white blood cells segmentation in color bone marrow images

Differential count of the various types of white blood cells (WBC) in bone marrow smears is used to help detect infection, anemia, and leukemia or to follow the process of treatment. However, locating, identifying, and counting the different classes of WBC manually are tedious and consuming time tasks that could be simplified by means an automatic analysis, in which segmentation is a crucial step. In this paper we present an approach to automatic cell segmentation within color bone marrow microscopic images, which is robust with regard to variable illuminant level conditions, and takes into account color components´ stability degrees. For each image pixel we get the similarity degree between its color and the system colors, what makes algorithm design much easier because allows to emulate experts´ image segmentation skills.