Národní úložiště šedé literatury Nalezeno 2 záznamů.  Hledání trvalo 0.00 vteřin. 
Multimodal Registration of Fundus Camera and OCT Retinal Images
Běťák, Ondřej ; Čmiel, Vratislav (oponent) ; Gazárek, Jiří (vedoucí práce)
This thesis is dealing with multimodal registration of retina from different scanning devices. With this multimodal registration is possible to enhance some details on the images which are crucial to detect different types of eye diseases (such as glaucoma, nerve fibre layer degradation, vessel degradation, etc.). The theoretical background of this thesis is followed by practical application which describes different types of registration of fundus, SLO and OCT images. Registration of fundus and SLO images is processed with spatial transformation. This thesis works with three different kinds of fundus and SLO image registration. First is the manual registration, which is the simplest one. The second one is automatic registration which is based on correlation. The results of these methods are discussed in conclusion. The third type – semi-automatic uses qualities of both previous methods and makes a compromise between accuracy and speed. Registration of fundus image and OCT B-scans is provided by two different methods. First is correlation-based registration, and second spatial-transformation-based method. All of the registration methods are provided with practical examples (algorithms) designed in Matlab.
Multimodal Registration of Fundus Camera and OCT Retinal Images
Běťák, Ondřej ; Čmiel, Vratislav (oponent) ; Gazárek, Jiří (vedoucí práce)
This thesis is dealing with multimodal registration of retina from different scanning devices. With this multimodal registration is possible to enhance some details on the images which are crucial to detect different types of eye diseases (such as glaucoma, nerve fibre layer degradation, vessel degradation, etc.). The theoretical background of this thesis is followed by practical application which describes different types of registration of fundus, SLO and OCT images. Registration of fundus and SLO images is processed with spatial transformation. This thesis works with three different kinds of fundus and SLO image registration. First is the manual registration, which is the simplest one. The second one is automatic registration which is based on correlation. The results of these methods are discussed in conclusion. The third type – semi-automatic uses qualities of both previous methods and makes a compromise between accuracy and speed. Registration of fundus image and OCT B-scans is provided by two different methods. First is correlation-based registration, and second spatial-transformation-based method. All of the registration methods are provided with practical examples (algorithms) designed in Matlab.

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