Národní úložiště šedé literatury Nalezeno 1 záznamů.  Hledání trvalo 0.00 vteřin. 

Warning: Requested record does not seem to exist.
Using advanced segmentation methods for images from TEM microscopes
Mocko, Štefan ; Chmelík, Jiří (oponent) ; Potočňák, Tomáš (vedoucí práce)
This master‘s thesis deals with the use of a convolutional neural networks for the segmentation task on images from transmission electron microscope. It also describes chosen neural network topology - U-NET, used augmentation techniques and programming environment. ThermoFisher Scientific (formerly FEI Czech Republic s.r.o.) provided data for this thesis. Obtained segmentation results are presented in the form of curves (ROC, PRC) and numerical values (ARI, DSC, Confusion matrices). Chosen U-NET topology achieved excellent results in the field of pixel-wise segmentation, and hopefully, these results will serve as a starting point for internal company research.

Chcete být upozorněni, pokud se objeví nové záznamy odpovídající tomuto dotazu?
Přihlásit se k odběru RSS.