Improvement of band segmentation in Epo images via column shift transformation with cost functions.

In recent years, the development of methodology and laboratory techniques for doping control (DC) of recombinant erythropoietin (rEpo) has become one of the most important topics pursued by doping control laboratories accredited by World Anti-Doping Agency (WADA). The software system GASepo has been developed within the international WADA project as a support for Epo doping control. Although a great number of functions for automatic image processing have been involved in this software, for Epo images with considerably distorted bands additional effort is required from the user to interactively correct the results of improper band segmentation. In this paper a problem of geometrically distorted bands is addressed from the viewpoint of how to transform the lanes in distorted Epo images in order to reach better band segmentation. A method of band straightening via column shift transformation has been proposed that is formulated as an optimization procedure with cost functions. The method involves several novel approaches: two-stage optimization procedure, four cost functions and selection of relevant columns. The developed band straightening algorithm (BSA) has been tested on real Epo images with distorted bands. Based on the evaluation scheme involving the GASepo software itself a recommendation is made for implementation of the method with the cost function based on correlation matrix. Estimates of computational complexity of the individual steps of BSA are also given.