The combination of classifiers has been proposed as a method allowing to improve the quality and the hardiness of recognition systems as compared to a single classifier. This paper describes a new segmentation scheme based on a combination of pixel classifications. The aim of this paper is to show the influence of the neighborhood information and of the number of classifiers used in the combination process. In the first part, we detail the ground of our study for an application. Then, we name the different steps of the new segmentation scheme. In the third part, we detail the classifiers combination step. In the next part, we present the different classifications results obtained on color microscopic images. Finally, we draw a conclusion on the improvement of the quality of the segmentation at the end of treatment.