Geo-thresholding for segmentation of fluorescent microscopic cell images

Pham, Tuan D. (2007) Geo-thresholding for segmentation of fluorescent microscopic cell images. In: Perner, Petra, and Salvetti, Ovidio, (eds.) Advances in Mass Data Analysis of Signals and Images in Medicine, Biotechnology and Chemistry. Lecture Notes in Computer Science, 4826 . Springer, Berlin, Germany, pp. 15-26.

[img] PDF (Published Version)
Restricted to Repository staff only

View at Publisher Website: http://dx.doi.org/10.1007/978-3-540-7630...
 
11
1


Abstract

Segmentation is an important research area in image analysis. In particular, effective segmentation methods play an essential role in the computerization of the analysis, classification, and quantification of biological images for high content screening. Image segmentation based on thresholding has many practical and useful applications because it is simple and computationally efficient. Different methods based on different criteria of optimality give different choices of thresholds. This paper introduces a method for optimal thresholding in gray-scale images by mimizing the variograms of object and background pixels. The mathematical formulation of the proposed technique is very easy for computer implementation. The experimental results have shown the superior performance of the new method over some popular models for the segmentation cell images.

Item ID: 2845
Item Type: Book Chapter (Research - B1)
ISBN: 978-3-540-76299-7
ISSN: 1611-3349
Keywords: image analysis; pattern recognition; bioinformatics
Date Deposited: 24 Sep 2009 23:49
FoR Codes: 08 INFORMATION AND COMPUTING SCIENCES > 0801 Artificial Intelligence and Image Processing > 080109 Pattern Recognition and Data Mining @ 50%
08 INFORMATION AND COMPUTING SCIENCES > 0801 Artificial Intelligence and Image Processing > 080106 Image Processing @ 50%
SEO Codes: 89 INFORMATION AND COMMUNICATION SERVICES > 8902 Computer Software and Services > 890205 Information Processing Services (incl. Data Entry and Capture) @ 100%
Downloads: Total: 1
More Statistics

Actions (Repository Staff Only)

Item Control Page Item Control Page