Details zur Publikation
Kategorie Textpublikation
Referenztyp Buchkapitel
DOI 10.1007/3-540-45783-6_52
Titel (primär) Segmenting microorganisms in multi-modal volumetric datasets using a modified watershed transform
Titel (sekundär) Pattern Recognition. 24th DAGM Symposium Zurich, Switzerland, September 16–18, 2002 Proceedings
Autor Bergner, S.; Pohle, R.; Al Zubi, S.; Tönnis, K.; Eitner, A.; Neu, T.R.
Herausgeber Van Gool, L.
Quelle Lecture Notes in Computer Science
Erscheinungsjahr 2002
Department FLOEK; GM
Band/Volume 2449
Seite von 429
Seite bis 437
Sprache englisch
Abstract

Aquatic interfaces in the environment are colonized by a large variety of pro- and eucaryotic microorganisms, which may be examined by confocal laser scanning microscopy. We describe an algorithm to identify and count the organisms in multi-channel volumetric datasets. Our approach is an intermediate-level segmentation combining a voxel-based classification with low-level shape characteristics (convexity). Local intensity maxima are used as seed points for a watershed transform. Subsequently, we solve the problem of over-segmentation by merging regions. The merge criterion is taking the depth of the ‘valley’ between adjacent segments into account. The method allows to make correct segmentation decisions without the use of additional shape information. Also this method provides a good basis for further analysis steps, e.g. to recognize organisms that consist of multiple parts.
dauerhafte UFZ-Verlinkung https://www.ufz.de/index.php?en=20939&ufzPublicationIdentifier=5354
Bergner, S., Pohle, R., Al Zubi, S., Tönnis, K., Eitner, A., Neu, T.R. (2002):
Segmenting microorganisms in multi-modal volumetric datasets using a modified watershed transform
In: Van Gool, L. (ed.)
Pattern Recognition. 24th DAGM Symposium Zurich, Switzerland, September 16–18, 2002 Proceedings
Lect. Notes Comput. Sci. 2449
Springer, Berlin, Heidelberg, New York, p. 429 - 437 10.1007/3-540-45783-6_52