Národní úložiště šedé literatury Nalezeno 2 záznamů.  Hledání trvalo 0.01 vteřin. 
Multiparametric segmentation of MR images
Chovanec, Ján ; Šmirg, Ondřej (oponent) ; Dvořák, Pavel (vedoucí práce)
The aim of the thesis was familiarity of segmentation methods for automatic segmentation of MR images, using multiparametrical display. The theoretical part focuses on the description of methods of segmentation techniques. In the practical part are implemented K-means and level-set method. The methods are tested on the images of the brain obtained by different sequences (T1, T1c, T2, FLAIR). Segmentation methods are implemented in the program MATLAB. Implemented segmentation accuracy is demonstrated on data which there are reports reference results. Evaluation methods is performed using different classifiers decision. The K-means method is tested different metrics and different combinations of the input image. Finally, both methods are compared with one another and visually evaluated against the reference image.
Multiparametric segmentation of MR images
Chovanec, Ján ; Šmirg, Ondřej (oponent) ; Dvořák, Pavel (vedoucí práce)
The aim of the thesis was familiarity of segmentation methods for automatic segmentation of MR images, using multiparametrical display. The theoretical part focuses on the description of methods of segmentation techniques. In the practical part are implemented K-means and level-set method. The methods are tested on the images of the brain obtained by different sequences (T1, T1c, T2, FLAIR). Segmentation methods are implemented in the program MATLAB. Implemented segmentation accuracy is demonstrated on data which there are reports reference results. Evaluation methods is performed using different classifiers decision. The K-means method is tested different metrics and different combinations of the input image. Finally, both methods are compared with one another and visually evaluated against the reference image.

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