|
|
Vektorová segmentace objemových medicínských dat založená na Delaunay triangulaci
Španěl, Michal ; Martišek, Dalibor (referee) ; Sochor, Jiří (referee) ; Kršek, Přemysl (advisor)
Image segmentation plays an important role in medical image analysis. Many segmentation algorithms exist. Most of them produce data which are more or less not suitable for further surface extraction and anatomical modeling of human tissues. In this thesis, a novel segmentation technique based on the 3D Delaunay triangulation is proposed. A modified variational tetrahedral meshing approach is used to adapt a tetrahedral mesh to the underlying CT volumetric data, so that image edges are well approximated in the mesh. In order to classify tetrahedra into regions/tissues whose characteristics are similar, three different clustering schemes are presented. Finally, several methods for improving quality of the mesh and its adaptation to the image structure are also discussed.
|
|
|
CAD System for 2D Drawing
Murín, Michal ; Chudý, Peter (referee) ; Kršek, Přemysl (advisor)
The Bachelor´s thesis is aimed at the design and creation of CAD system for 2D drawing. It introduces the use of computers in manufacturing and the advantages the use of computers brings, general definition of CAD systems and requirements imposed on them. The thesis contains the design of generated CAD system, and as a practical part it introduces implementation of the designed application. Finally it summarizes what has been achieved in developing and what could potentially be achieved in further expansion of the application in the future.
|
|
|
Medical Image Data Compression
Šebek, Jiří ; Bařina, David (referee) ; Kršek, Přemysl (advisor)
This thesis deals with several lossless methods of image compression. The main goal is to achieve the best compression ratio for set of medical images. This paper provides brief introduction into the data compression theory. It also contains design of image compression and description of designed compression modules implementation. Also the verifi cation of suitability of designed method for medical images compression is involved.
|
|
|
Interactive Human Tissues 3D Modelling by CT/MR Data
Zachar, Lukáš ; Štancl, Vít (referee) ; Kršek, Přemysl (advisor)
The aim of this thesis is to create a system, which would make a 3D model of tissues based on CT or MRI scans. Input data is in the DICOM format. Selection of tissues is done by the user by specifying range of values in scans. The current selection is highlighted. The creation of polygonal model is done by the Marching cubes algorithm. It is possible to save the model in format VRML or STL.
|
|
|
Image Segmentation Using Height Maps
Moučka, Milan ; Kršek, Přemysl (referee) ; Španěl, Michal (advisor)
This thesis deals with image segmentation of volumetric medical data. It describes a well-known watershed technique that has received much attention in the field of medical image processing. An application for a direct segmentation of 3D data is proposed and further implemented by using ITK and VTK toolkits. Several kinds of pre-processing steps used before the watershed method are presented and evaluated. The obtained results are further compared against manually annotated datasets by means of the F-Measure and discussed.
|
|
|
Skeleton Extraction from Polygonal Meshes
Borek, Ondřej ; Kršek, Přemysl (referee) ; Španěl, Michal (advisor)
This bachelor's thesis deals with skeleton extraction from 3D objects. The presented technique for skeleton extraction from incomplete points cloud is based on ROSA (Rotational Symmetry Axis) method, while the searching for rotational symmetry axis was optimized. The method is resistant to missing data and is suitable for objects made from cylindrical parts and joints of that parts (for example human and animals bodies). In experiments, both the influence of object properties (for example missing data, chill mark, shape) and the influence of method's parameters were examined.
|
|
| |
|
|
Tooth Detection on Jaw 3D Computer Polygonal Model
Hulík, Rostislav ; Španěl, Michal (referee) ; Kršek, Přemysl (advisor)
This document discusses a concept and implementation of algorithms for teeth detection on 3D polygonal jaw model. At first, I describe possible shape detection techniques on three dimensional computer model, including utilization just in my case. After it, I analyze filtration problems of obtained model segments in order to reliably separate regions of tooth-arch from the rest of jaw. I included all these pieces of knowledge into a final application. Here, it is possible to choose from two user interfaces, first, classic user interface which demonstrates possible utilization in real world and second, testing interface which demonstrates functions of each detection and filtration method used in program and their effect on detection. Application is written in C++ language in development environment of MS Visual Studio 2005 and compiled with MS VS internal compiler. Tested was under MS Windows XP and MS Windows Vista OS.
|
|
|
CAD System for 3D Modelling
Arlet, Filip ; Chudý, Peter (referee) ; Kršek, Přemysl (advisor)
This thesis deals with the creation of 3D CAD drawing system. Includes Introduction to and brief description of CAD systems. The main focus of thesis is design and implementation of 3D CAD system. Finally, we evaluated the results and identifying opportunities for further development.
|
|
|
Education Computer Program for Demonstration Methods of 3D Objects Texturing
Kukla, Michal ; Španěl, Michal (referee) ; Kršek, Přemysl (advisor)
This work is focused on developing an application for demonstration methods of 3D objects texturing. Work contains theoretical description of particular texturing methods which create base for designing subject of demonstration. Application requirements are analysed and applied to create aplication design. Aproaches used in implementing particular texturing methods and description of application controls are discussed in final part. Application can be used as demonstration tool in lectures or as study material for learners.
|
guest ::
RSS feed.