A New Watershed Algorithm for Cellular Image Segmentation Based on Mathematical Morphology

Abstract

A new watershed algorithm based on mathematical morphology is proposed and applied to cellular image segmentation. The improvement segmentation method of the watershed algorithm based on the marker introduce the idea of morphological reconstruction during the pretreatment, at the same time, use a relatively new method of coercing calibration of the minimum in the watershed transform. With the original method of simulation experiments, the method can be more accurate segmentation results. Compared with other tradition methods, requires fewer computations and simpler parameters and can more efficiently reduce the over-segmentation of the watershed algorithm.