|
|
Affine registration of native and contrast-enhanced CT brain images
Chmelík, Jiří ; Mézl, Martin (referee) ; Walek, Petr (advisor)
This thesis is dealing with problem of brain images registration aquired by computed tomography. At the beginning is explanation of image geometrical transformation methods, notably affine transformation. Following part of text the is dealing with interpolation methods issues, calculation of similarity criterion and subsequent optimalization. All issues are handled especially for three-dimensional data. Second part of this work is practical sample of MatLab® program enviroment for registration of acquired frames by affine tranformation. In this program is algorithm for removement of stair-step artefact, under head pillow and patient’s desk, too. As an optimalization algorithm is used control random search (CRS) methode. Due to medical images type, which are distributed in DICOM format, is included process for their load and save at this work.
|
|
|
Segmentation of carbon nanocones in TEM images using generalized Hough transform
Sladký, Vladimír ; Odstrčilík, Jan (referee) ; Walek, Petr (advisor)
Bachelor thesis deals with automatic detection of carbon nanostructures in TEM images using generalized Hough transform. There is described the theory of Hough transform in order to detect analytic as well as general structures in images. According to the characteristics of carbon nanostructures TEM images synthetic test images, that are preprocessed by morphological operations and thresholding with global threshold, are created. Hough transform algorithm that detects nanocones in synthetic images of carbon nanocone structures is created. Success and accuracy of detection is tested changing the parameters of artificial images or level of preprocessing.
|
|
|
Automatic Classification of Antibiotic Discs Photographs
Hesko, Branislav ; Kolář, Radim (referee) ; Walek, Petr (advisor)
This bachelor’s thesis deals with problematics of automatical classification of antibiotical discs photographies.The aim of this work is to apply several methods on images to create output with classified images. The problem is split into preprocessing and classification by itself. Preprocessing is solved with the use of Canny’s edge detector, Hough transform for detecting lines and circles, alignment, rotation and cutting out text with individual letters. Classification is then realised using neural network and minimum distance between pixels. Explanations and analysis of this methods should help to create theoretical overview on analysed problematics. The application of these algorithms in practical part will show some persisting imperfections of choosen processing caused by low quality of photographies of antibiotical discs.
|
|
|
Measurements of Nanoparticles Infrared Absorption
Peprníčková, Anna ; Walek, Petr (referee) ; Sekora, Jiří (advisor)
This diploma thesis is focused on measurements of nanoparticles infrared absorption. In project is made literar research of sensors in part of IR area, principal design of detector controled by microcontroller for measurement absorption properties of solutions of nanoparticles and microparticles in IR area with diode detector and bank of optical filtres. According to this design of device microcontroller and display device was chosen. This work contains program design for microcontroler and display unit.
|
|
|
Automatic detection of microaneurysms in fundus images
Klímová, Markéta ; Walek, Petr (referee) ; Kolář, Radim (advisor)
Diabetic retinopathy is a serious complication of diabetes mellitus. It develops as a result of total damage of vessels caused by hyperglycemia and it is one of major causes of blindness. The microaneurysms are the first clinically observed pathologies of diabetic retinopathy. The aim of this bachelor thesis is to propose and to implement an automated microaneurysm detector. Teoretical part describes the eye anatomy, diabetic retinopathy and some existing methods of automated detection. Next the implemented solution is described and the results of the detectin are evaluated.
|
|
|
The use of wavelet transform for image data fusion
Demel, Jan ; Jan, Jiří (referee) ; Walek, Petr (advisor)
This bachelor thesis analyzes the possibility of using the wavelet wavelet transform in multifocal image fusion. First, it describes the basic principle of the wavelet transform and its use for image data fusion. Basic description of the fusion and its principles follows, including a description of the basic fusion rules. Actual software solution for wavelet decomposition and fusion is described in the fourth chapter of this work. In this thesis there is also a quantitative statistical comparison of different rules for fusing decomposed images and their evaluation along with examples of created multifocal images. GUI for image fusion was created where the user can set various parameters to achieve the best results.
|
|
|
Narrow Band Filtering of ECG Signals
Němeček, Tomáš ; Walek, Petr (referee) ; Kozumplík, Jiří (advisor)
Main objective of this bachelors thesis, was to learn about issues and possibilities of ECG filtration. This thesis is focused on narrowband filtration by Lynn’s filters. The objective for this thesis was to design filters for filtration of interferences called drift and brum. Both of them should not affect the relevant part of signal.
|
|
|
Simulation of the CT X-ray Detectors
Koutek, Petr ; Walek, Petr (referee) ; Drastich, Aleš (advisor)
The bachelor thesis deals with the basic properties of the detectors used in X-ray CT, and their influence on the choice of acquisition parameters. The theoretical part summarizes the general issues of projection reconstruction view and basic characteristics of the detectors. In the practical part is created simulator which simulate the effect of deacy time, afterglow and the light output.
|
|
|
Removal of Anesthesia Tube from Pediatric CT Data
Šejnohová, Marie ; Čmiel, Vratislav (referee) ; Walek, Petr (advisor)
The goal of this semestral thesis is to detect and subsequently to eliminate an anaesthesiological tube from a pediatric CT data using a Hough transform. It describes particular edge detectors based on the first and the second differences. In addition, it explains a principle of the edge detection using to this detectors. Then there is talked about the Hough Transform where is described a parametric space for lines and circles detection. Here follows a description of image to the parametric space. In a practical part there is implementation of the edge detection and the Hough transform. The Hough space must be normalized to better evaluation. At the evaluation there are found a concentric cicrles corresponding with edges of an anaesthesiological tube which is then possible to remove.
|
|
|
Blind Image Deconvolution of Electron Microscopy Images
Schlorová, Hana ; Odstrčilík, Jan (referee) ; Walek, Petr (advisor)
V posledních letech se metody slepé dekonvoluce rozšířily do celé řady technických a vědních oborů zejména, když nejsou již limitovány výpočetně. Techniky zpracování signálu založené na slepé dekonvoluci slibují možnosti zlepšení kvality výsledků dosažených zobrazením pomocí elektronového mikroskopu. Hlavním úkolem této práce je formulování problému slepé dekonvoluce obrazů z elektronového mikroskopu a hledání vhodného řešení s jeho následnou implementací a porovnáním s dostupnou funkcí Matlab Image Processing Toolboxu. Úplným cílem je tedy vytvoření algoritmu korigujícícho vady vzniklé v procesu zobrazení v programovém prostředí Matlabu. Navržený přístup je založen na regularizačních technikách slepé dekonvoluce.
|
guest ::
