Towards a Fully Automated Tissue Cell Segmentation Method

Warning

This publication doesn't include Institute of Computer Science. It includes Faculty of Informatics. Official publication website can be found on muni.cz.
Authors

SVOBODA David

Year of publication 2004
Type Article in Proceedings
Conference Visualization, Imaging, and Image Processing
MU Faculty or unit

Faculty of Informatics

Citation
Web http://www.actapress.com/PaperInfo.aspx?PaperID=18789&reason=500
Field Informatics
Keywords Biomedical image segmentation; Adaptive thresholding; Gradient based thresholding; Region labeling
Description In this paper, an automatic method for tissue cell localization is proposed. It is based on the principle of adaptive thresholding. While the general adaptive thresholding method requires setting of some parameters by user, a novel algorithm chooses suitable thresholds and image division on its own. The resulting binary image is then submitted to a region labeling procedure. Each individual region is inspected and tested for suitability for further processing. Finally, each region is marked by one marker. Feasibility of this approach has already been successfully tested on 3D colon tissue images.
Related projects:

You are running an old browser version. We recommend updating your browser to its latest version.

More info