Thesis Details
Nelineární filtrace velkých 3D obrazových dat
This bachelor thesis deals with design and effective implementation of nonlinear filters, bilateral filter and non-local means filter, for denoising 3D image data. The implemented filters are optimized by various techniques such as parallel processing, integral image, sampling etc. This thesis project includes cross-platform solution of these filters in C\# language and two demonstration applications -- a GUI application for Windows and a cross-platform console application -- demonstrating the use of the library. The performance and output of implemented filters were tested and compared against open source reference filters (Itk, scikit-image), with the 3D bilateral filter implementation being up to $30×$ faster than the available implementation of the Itk filter and the implementation of the 3D non-local means filter is approximately $2×$ faster than the scikit-image implementation
nonlinear filters, bilateral filter, non-local menas filter, 3D bilateral filter, 3D non-local means filter, non-linear filters for volumetric data, nonlinear filters for 3D image data, fast bilateral filter, fast non-local means filter
Burget Lukáš, doc. Ing., Ph.D. (DCGM FIT BUT), člen
Holík Lukáš, doc. Mgr., Ph.D. (DITS FIT BUT), člen
Martínek Tomáš, doc. Ing., Ph.D. (DCSY FIT BUT), člen
Matoušek Petr, doc. Ing., Ph.D., M.A. (DIFS FIT BUT), člen
@bachelorsthesis{FITBT23513, author = "Michael \v{S}kr\'{a}\v{s}ek", type = "Bachelor's thesis", title = "Neline\'{a}rn\'{i} filtrace velk\'{y}ch 3D obrazov\'{y}ch dat", school = "Brno University of Technology, Faculty of Information Technology", year = 2022, location = "Brno, CZ", language = "czech", url = "https://www.fit.vut.cz/study/thesis/23513/" }