ABSTRACT

This chapter presents the principles of morphological segmentation. Segmentation is one of the key problems in image processing. In fact, one should say segmentations because there exist as many techniques as there are specific situations. An original method of segmentation based on the use of watershed lines has been developed in the framework of mathematical morphology. The chapter describes some useful morphological tools for segmentation: gradient, top-hat transform, distance function, geodesic distance function, and geodesic reconstructions. The gradient image is used in the watershed transformation, because the main criterion for the segmentation in many applications is the homogeneity of the gray values of the objects present in the image. The problems encountered in the segmentation process will be best illustrated by presenting a complete and typical segmentation problem in the field of automated cytology. The oversegmentation produced by direct construction of the watershed line is due to the fact that every regional minimum becomes the center of a catchment basin.