|
|
Blind Image Deconvolution in STEM mode of Electron Microscope
Valterová, Eva ; Walek, Petr (oponent) ; Potočňák, Tomáš (vedoucí práce)
Blind image deconvolution is method, which restore the true image and point spread function simultaneously. The goal of this paper is to introduce several methods of blind deconvolution and find the optimal method for reconstruction of the true image and point spread function of images from scanning transmission electron microscope. The alternating minimization algorithm is assumed as the most convenient for blind deconvolution problem. Then it is modified and tested. The proposed algorithm properties are tested on artificially degraded data and the real data from scanning transmission electron microscope. The algorithm efficiency is evaluated by several evaluating criteria. The algorithm limitations are determined and its area of use is specified.
|
|
| |
|
|
Radiační poškození vzorků v nízkovoltové transmisní elektronové mikroskopii
Vykydal, Václav ; Valterová, Eva (oponent) ; Kolář, Radim (vedoucí práce)
Práce je zaměřena na vliv radiačního poškození vzorků v nízkonapěťové transmisní elektronové mikroskopii. V práci se nachází obecný popis transmisních elektronových mikroskopů a jejich důležitých částí. Je zde popsán způsob poškození vzorků ozářených primárním svazkem elektronů, jak se připravují vzorky pro elektronovou mikroskopii a k jaké degradaci vzorků dochází z hlediska materiálu vzorku a časovému zatížení primárním elektronovým svazkem.
|
|
|
Processing of high-resolution retinal images
Vraňáková, Sofia ; Chmelík, Jiří (oponent) ; Valterová, Eva (vedoucí práce)
The master’s thesis is focused on the processing of high-resolution retinal images. The aim of this work is to obtain images of higher quality from a sequence of low-quality frames. The frames are first pre-processed by using bilateral filtering and contrast enhancement. The shift between the frames in the imaging sequence is estimated using phase correlation, and these frames are then fused together using the averaging through the frames and the super-resolution technique, more specifically regularization based on bilateral total variance. The resulting median quality scores of obtained images are PIQUE 0.2600, NIQE 0.0701, and BRISQUE 0.3936 for the averaging technique and PIQUE 0.1063, NIQE 0.0507, and BRISQUE 0.1570 for super-resolution technique.
|
|
|
Pletysmografie pro zpracování retinálních sekvencí
Plavcová, Daniela ; Valterová, Eva (oponent) ; Kolář, Radim (vedoucí práce)
Zrak je jedním z pěti lidských smyslů a je velmi důležitým pro zkoumání blízkého i vzdáleného okolí. Tomu ovšem brání různé oční vady, které mohou souviset s cévním systémem sítnice a pulzacemi, které jsou na ní pozorovatelné. Tato práce se zabývá zkoumáním souvislostí mezi zmíněnými pulzacemi a onemocnění glaukomem. Pro hledání spojitostí mezi těmito dvěma aspekty jsou použité videozáznamy ze sítnice, s jejíž pulzací je dál pracováno ve formě 1D signálu, a to především ve spektrální oblasti.
|
|
|
Segmentace cév ve snímcích sítnice s vysokým rozlišením
Svobodová, Sabina ; Odstrčilík, Jan (oponent) ; Valterová, Eva (vedoucí práce)
Tato práce se zabývá návrhem a realizací algoritmu pro segmentaci cév oční sítnice ve snímcích s vysokým rozlišením. Jako metoda byla zvolena neuronová síť se dvěma skrytými vrstvami. Bylo získáno celkem 7 příznaků, a to z přizpůsobené filtrace na základě tloušťky cév, z texturní analýzy a jednotlivé jasové pixely. V rámci práce byla manuálně anotována celá databáze pro implementci algoritmu i výsledné vyhodnocení. Dosažená průměrná senzitivita dosáhla hodnoty 80%, specificita 97%, a úspěšnost segmentace cév (Dice skóre) 59%.
|
|
|
Spatial registration of partially overlapping retinal images
Žiak, Milan ; Harabiš, Vratislav (oponent) ; Valterová, Eva (vedoucí práce)
Adaptive optics give us opportunity to capture high resolution images of retina, even we are able to detect cones. Spatial registration of retina images has to be done due to scanning process of capturing, because current opthalmoscops with adaptive optics aren't able to capture whole area of retina. Diploma thesis demonstrates basic princip of automatic spatial registration of overlaping images. It uses constellation features for matching some of the detected cones. K-means combinate wiht RANSAC is used for outlier detection. Inliers matching pairs are then used to define a affine transformation matrix. This method was aplied on dataset retina images from AO-FIO modality and evaluation of quality was computed according to normalized mutual information. Result shows that this metod is suitable for registration AO-FIO images with "cell-to-cell" accuracy.
|
|
|
Spatial registration of partially overlapping retinal images
Žiak, Milan ; Harabiš, Vratislav (oponent) ; Valterová, Eva (vedoucí práce)
Adaptive optics give us opportunity to capture high resolution images of retina, even we are able to detect cones. Spatial registration of retina images has to be done due to scanning process of capturing, because current opthalmoscops with adaptive optics aren't able to capture whole area of retina. Diploma thesis demonstrates basic princip of automatic spatial registration of overlaping images. It uses constellation features for matching some of the detected cones. K-means combinate wiht RANSAC is used for outlier detection. Inliers matching pairs are then used to define a affine transformation matrix. This method was aplied on dataset retina images from AO-FIO modality and evaluation of quality was computed according to normalized mutual information. Result shows that this metod is suitable for registration AO-FIO images with "cell-to-cell" accuracy.
|
|
|
Automatic Adaptive Optics Retinal Images Montaging
Valterova, Eva
The adaptive optics images capture limited field of view. Nevertheless, the quantitativeretina assessment requires analysis over extended areas captured by images on various retina positions.The fully automated method for image registration and montaging is presented. The methodutilizes scale invariant feature transform (SIFT) for feature extraction from preprocessed images.The method is tested on 200 images of normal healthy patients. The montages of 20 eyes were createdand evaluated by normalized mutual information metrics and the results showed high alignmentaccuracy.
|
|
|
Automated Fovea Center Estimation In Adaptive Optics Images
Valterova, Eva
The adaptive optics (AO) is an insightful tool with high potential. Since the first demonstration in ophthalmology has undergone immense growth in its diagnostic application, mainly because the AO enables to capture retina in vivo with resolution on the cellular level. In the center of the retina is macula, containing the fovea. The fovea detection is possible with utilizing the knowledge of its characteristical properties. We developed and applied two methods for fovea center estimation. The first method is based on image maximum detection. The second is based on the 2D Gaussian curve fitting. The first method has proved better results in comparison with manual grading. The measured difference was 32_x0006_27 pixels. The second approach has in comparison with manual grading slightly higher difference equal to 108_x0006_64 pixels. Both of the methods estimated the foveal center within the expected foveal area.
|
host ::
RSS.