Comparing marker definition algorithms for watershed segmentation in microscopy images
Segmentation is often a critical step in image analysis. Microscope image components show great variability of shapes, sizes, intensities and textures. An inaccurate segmentation conditions the ulterior quantification and parameter measurement. The Watershed Transform is able to distinguish extremel...
| Autores: | , , |
|---|---|
| Formato: | artículo |
| Estado: | Versión publicada |
| Fecha de publicación: | 2008 |
| País: | Argentina |
| Recursos: | Universidad Nacional de La Plata |
| Repositorio: | SEDICI (UNLP) |
| Idioma: | inglés |
| OAI Identifier: | oai:sedici.unlp.edu.ar:10915/9639 |
| Acesso em linha: | http://sedici.unlp.edu.ar/handle/10915/9639 |
| Access Level: | acceso abierto |
| Palavra-chave: | Ciencias Informáticas Clustering Segmentation Image processing software |
| Resumo: | Segmentation is often a critical step in image analysis. Microscope image components show great variability of shapes, sizes, intensities and textures. An inaccurate segmentation conditions the ulterior quantification and parameter measurement. The Watershed Transform is able to distinguish extremely complex objects and is easily adaptable to various kinds of images. The success of the Watershed Transform depends essentially on the existence of unequivocal markers for each of the objects of interest. The standard methods of marker detection are highly specific, they have a high computational cost and they determine markers in an effective but not automatic way when processing highly textured images. This paper compares two different pattern recognition techniques proposed for the automatic detection of markers that allow the application of the Watershed Transform to biomedical images acquired via a microscope. The results allow us to conclude that the method based on clustering is an effective tool for the application of the Watershed Transform. |
|---|