The Morphological Approach to Segmentation: The Watershed Transformation

By Serge Beucher, F. Meyer. Mathematical Morphology in Image Processing, 2018

668 citations recorded by the source corpus.

Segmentation is one of the key problems in image processing. ln fact, one should say segmentations because there exist as many techniques as there are specifie situations. Among them, gray-tone images segmentation is very important and the relative techniques may be divided into two groups: the techniques based on contour detection and those involving region growing. Many authors have tried to define general schemes of contour detection using low-level tools [1,2]. Unfortunately, because they work at a very primitive level, a great number of algorithms must be used to emphasize their results. An original method of segmentation based on the use of watershed lines has been developed in the framework of mathematical morphology. This technique, which may appear to be close to the region-growing methods, leads in fact to a general methodology of segmentation and has been applied with success in many different situations. ln this chapter, the principles of morphological segmentation will be presented and illustrated by means of examples, starting from the simplest ones and introducing step by step more complex segmentation tools. ln Section II, we shal! review briefly various morphologie al tools which are used throughout this chapter. These basic transformations are useful for the description of sorne algorithms used in morphological segmentation. We shall not introduce the basic notions of mathematical morphology; the reader not farniliar with them is invited to refer to [3,4].

Subfields: Artificial Intelligence, Biophysics, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/10c0f65c03f9d7fa120205d4da97977df988d0c8

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Biophysics

In Computer Vision and Pattern Recognition

Citations in the corpus

Where are the Blobs: Counting by Localization with Point Supervision (2018, methodology): “es generated by the line split method. 2. Watershed split method. This consists of global and local segmentation procedures. For the global segmentation, we apply the watershed segmentation algorithm [33] globally on the input image where we set the ground-truth point-annotations as the seeds. The s”
Star-convex Polyhedra for 3D Object Detection and Segmentation in Microscopy (2019, methodology): “These include classical thresholding approaches with pixel-grouping via connected component, morphological methods based on the watershed transform [4, 16, 7], and optimization via graphcuts [5].”
Versatile and efficient pore network extraction method using marker-based watershed segmentation. (2017, methodology): “The version used here is available in the SCIKIT-IMAGE package (aka SKIMAGE) and is a marker-based implementation [45].”