Automatic segmentation and recognition of pathomorphological microscopic images

This paper is concerned with quantitative analysis of color biomedical images. We take into account microscopic cytological and histological images. The aim of the examination is to extract two types of object from a set of images and evaluate their count and area. An essential step in the recognition procedure is image segmentation, due to the poor quality of the source images. We test some segmentation techniques including the combination of color discrimination and region based methods.