A Comparative Study of Three Marker Detection Algorithms in Electron Tomography

Patrick Trampert, Sviatoslav Bogachev, Nico Marniok, Tim Dahmen, Philipp Slusallek

In: Microscopy & Microanalysis - The Official M&M 2016 Proceedings. Microscopy & Microanalysis (M&M-2016) July 24-28 Columbus OH United States Seiten 1044-1045 22 Suppl 3 Cambridge University Press 2016.


We conducted a comparative study of three widely used algorithms for the detection of fiducial$\$nmarkers in electron microscopy images. The algorithms were applied to four datasets from different sources. For$\$nthe purpose of obtaining comparable results, we introduced figures of merit and implemented all three algorithms$\$nin a unified code base to exclude software-specific differences. The application of the algorithms revealed that$\$nnone of the three algorithms is superior to the others in all cases. This leads to the conclusion that the choice of a$\$nmarker detection algorithm highly depends on the properties of the dataset to be analyzed, even within the$\$nnarrowed domain of electron tomography

Deutsches Forschungszentrum für Künstliche Intelligenz
German Research Center for Artificial Intelligence