Segmentation and supervised classification of image objects in Epo doping-control

Authors: Bajla, Ivan¹; Rublík, František²; Arendacká, Barbora²; Farkaš, Igor²; Hornišová, Klára²; Štolc, Svorad³; Witkovský, Viktor²

Source: Machine Vision and Applications, Volume 20, Number 4, June 2009 , pp. 243-259(17)

Publisher: Springer

Buy & download fulltext article:

Price: $47.00 plus tax (Refund Policy)

Abstract:

A software system Gel Analysis System for Epo (GASepo) has been developed within an international WADA project. As recent WADA criteria of rEpo positivity are based on identification of each relevant object (band) in Epo images, development of suitable methods of image segmentation and object classification were needed for the GASepo system. In the paper we address two particular problems: segmentation of disrupted bands and classification of the segmented objects into three or two classes. A novel band projection operator is based on convenient object merging measures and their discrimination analysis using specifically generated training set of segmented objects. A weighted ranks classification method is proposed, which is new in the field of image classification. It is based on ranks of the values of a specific criterial function. The weighted ranks classifiers proposed in our paper have been evaluated on real samples of segmented objects of Epo images and compared to three selected well-known classifiers: Fisher linear classifier, Support Vector Machine, and Multilayer Perceptron.

Keywords: Image segmentation; Statistical classification; Weighted ranks classifier; Epo doping-control; Epo gel image

Document Type: Research article

DOI: http://dx.doi.org/10.1007/s00138-007-0120-0

Affiliations: 1: Smart Systems Division, Austrian Research Centers GmbH—ARC, 2444, Seibersdorf, Austria, Email: ivan.bajla@arcs.ac.at 2: Department of Theoretical Methods, Institute of Measurement Science, Slovak Academy of Sciences, Dúbravská cesta 9, 84101, Bratislava, Slovak Republic 3: Department of Theoretical Methods, Institute of Measurement Science, Slovak Academy of Sciences, Dúbravská cesta 9, 84101, Bratislava, Slovak Republic, Email: umerstol@savba.sk

Publication date: 2009-06-01

Segmentation and supervised classification of image objects in Epo doping-control

Buy & download fulltext article:

Tools

Key

Text size:

Useful pages