Book ChapterDOI
Watershed, Hierarchical Segmentation and Waterfall Algorithm
Serge Beucher
- pp 69-76
Reads0
Chats0
TLDR
This paper presents a technique based on mosaic images and on the computation of a watershed transform on a valued graph derived from the mosaic images that leads to a hierarchical segmentation of the image and considerably reduces over-segmentation.Abstract:
A major drawback when using the watershed transformation as a segmentation tool comes from the over-segmentation of the image. Over-segmentation is produced by the great number of minima embedded in the image or in its gradient. A powerful technique has been designed to suppress over-segmentation by a primary selection of markers pointing out the regions or objects to be segmented in the image. However, this approach can be used only if we are able to compute the marker set before applying the watershed transformation. But, in many cases and especially for complex scenes, this is not possible and an alternative technique must be used to reduce the over-segmentation. This technique is based on mosaic images and on the computation of a watershed transform on a valued graph derived from the mosaic images. This approach leads to a hierarchical segmentation of the image and considerably reduces over-segmentation.read more
Citations
More filters
Journal ArticleDOI
The watershed transform: definitions, algorithms and parallelization strategies
TL;DR: A critical review of several definitions of watershed transform and associated sequential algorithms is presented in this paper, where the need to distinguish between definition, algorithm specification and algorithm implementation is pointed out.
Journal ArticleDOI
Improved watershed transform for medical image segmentation using prior information
TL;DR: An improvement to the watershed transform is presented that enables the introduction of prior information in its calculation, and a method to combine the watershedtransform and atlas registration, through the use of markers is introduced.
Journal ArticleDOI
Automatic watershed segmentation of randomly textured color images
TL;DR: The segmentation procedure has been found to be very robust, producing good results not only on granite images, but on the wide range of other noisy color images as well, subject to the termination criterion.
Journal ArticleDOI
A hybrid 3D watershed algorithm incorporating gradient cues and object models for automatic segmentation of nuclei in confocal image stacks
Gang Lin,Umesh Adiga,Umesh Adiga,Kathy Olson,John F. Guzowski,Carol A. Barnes,Badrinath Roysam +6 more
TL;DR: This work has shown that tight clustering of nuclei in 3D confocal microscope images is a common source of segmentation error, and a compelling need to minimize these errors for constructing highly automated scoring systems.
Journal ArticleDOI
Watershed Cuts: Minimum Spanning Forests and the Drop of Water Principle
TL;DR: The consistency of these watersheds is established, and it is proved, through an equivalence theorem, their optimality in terms of minimum spanning forests and the proposed algorithm is the most efficient existing algorithm, both in theory and in practice.
References
More filters
Dissertation
Segmentation d'images et morphologie mathématique
TL;DR: In this article, the morphologie mathematique is used for the segmentation of images of gris and eaux, and the concept of marquage des regions a segmenter is introduced.
Dissertation
La geodesie numerique en morphologie mathematique. Application a la detection des microcalcifications en mammographie numerique
TL;DR: In this paper, les h-extrema transformations of a morphologie mathematique (mm) are defined as a set of transformations which permet de valuer, sur des criteres de contraste, les extrema d'une image.