Authors:
Jan Schier
and
Bohumil Kovář
Affiliation:
Institute of Information Theory and Automation of the ASCR, Czech Republic
Keyword(s):
Colony counter, Yeast colonies, Image segmentation, Fast radial transform.
Related
Ontology
Subjects/Areas/Topics:
Algorithms and Software Tools
;
Bioinformatics
;
Biomedical Engineering
;
Image Analysis
;
Pattern Recognition, Clustering and Classification
Abstract:
A method for counting yeast colonies in images of Petri dishes, based on the fast radial transform by Loy and Zelinsky, is introduced and evaluated in the paper. The characteristic properties of the images of yeast colonies, as produced by the setup
used in the cooperating genetics laboratory, are described, the underlying counting algorithm is reviewed and the performance of the method is evaluated, using a test set of 245 images. The images, included in this set, typically contained between 10 and 70 colonies per dish, with relative coverage of the diosh less than 10% of the area. The average counting error (missed colonies) on this set was under 4%.
A tool, implementing the method, has been developed in Matlab. The motivation to develop our own colony counting program, instead of using a commercial solution, was to reuse the imaging equipment already existing in the laboratory and to adapt the tool to the needs of this laboratory. The tool provides a batch mode for processing of l
arger image sets prepared beforehand in the darkroom and it automatizes the process of counting as much as possible. It is available for download or can requested from the authors of the paper, in both cases free on charge.
(More)