Táto práce se zabývá použitím hlubokého učení neuronových sítí ke zvýšení rozlišení obrázků, které obsahují obličeje. Tato metoda najde uplatnění v různých oblastech, zejména v bezpečnosti, například, při bezpečnostním incidentu, kdy policie potřebuje identifikovat podezřelého z nahraného videa ze sledovací kamery. Cílem této práce je navrhnout minimálně dvě architektury neuronových sítí, které budou pracovat se sekvencí snímků, a porovnat je s metodami zpracování jediného snímku. Pro tento účel je také vytvořena nová trénovací množina, obsahující sekvenci snímku obličeje. Metody zpracování jednoho snímku jsou natrénované na nové množině. Dále jsou navrženy nové metody zvětšení obrázků na základě sekvence snímků. Tyto metody jsou založené na U-Net modelu, který je úspěšný v segmentaci, ale také v superrozlišení. Pro zlepšení architektury byly použity reziduální bloky a jejich modifikace, a navíc také percepční ztrátová funkce, která dovoluje vyhnout se rozmazání a získání více detailů. První čast této práce je věnovana popisu neuronových sítí a některých architektur, jejichž modifikace mohou být použity v superrozlišení. Druhá část se poté zabývá popisem metod pro zvýšení rozlišení obrazu pomocí jednoho snímku, několika snímků a videa. Ve třetí části jsou popsány navržené metody a experimenty a v poslední části porovnaná metod založených na jednom snímku a několika snímcích. Navržené metody jsou schopny získat více detailů v obraze, ale mohou produkovat artefakty. Ty lze ale poté eliminovat pomocí filtru, například Gaussova. Nové metody méně selhávají při detekci obličejů, a to je podstatné u identifikace člověka v případě incidentu.

This thesis deals with an autonomous single-channel deinterleaving. An autonomous single-channel deinterleaving is a separation of the received sequence of impulses from more than one emitter to sequences of impulses from one emitter without a human assistance. Methods used for deinterleaving could be divided into single-parameter and multiple-parameter methods according to the number of parameters used for separation. This thesis primarily deals with multi-parameter methods. As appropriate methods for an autonomous single-channel deinterleaving DBSCAN and variational bayes methods were chosen. Selected methods were adjusted for deinterleaving and implemented in programming language Python. Their efficiency is examined on simulated and real data.

This diploma project is showen possibilities in classification of genomic sequences with CGR and FCGR methods in pictures. From this picture is computed classificator with BCM. Next here is written about the programme and its opportunities for classification. In the end is compared many of sequences computed in different options of programme.

Magnetic resonance imaging is a routine and powerful diagnostic technique capable of providing detailed information about the structure and composition of the tissues. This diploma thesis is concerned with the mechanisms of contrast origin and contrast modifications by molecular and nanoparticle contrast agents. First sections of the thesis summarize basic knowledge about pulse sequences and it aims to provide an overview on MRI contrast agent with a special emphasis on paramagnetic gadolinium contrast agents and superparamagnetic nanoparticles. The main purpose of this study is to develop the software called MRICalc, which is able to optimize contrast in MRI images. Based on analysis of signal formula of typical pulse sequences, MRICalc is able to propose the parameters of the pulse sequence for compartment-specific enhancement of the contrast. User chooses from the list of the samples and after calculation he obtains the values of echo time, repetition time and flip angle, all of which simultaneously seem to create the appropriate setting to enhance the contrast. MRICalc also allows to plot contrast function with respect to the chosen parameter. Software, including its graphical user interface, is designed in Python. The sample consists from solution of CuSO4 and distilled water was designed to verify the correct function of MRICalc. Sulphate represents a contrast agent. Preclinical MR system Bruker BioSpec 94/30 USR located at Institute of Scientific Instruments of the ASCR, v.v.i was used to measure contrast curve of FLASH pulse sequence, which is a typical representative of gradient echo. Results of the measurement were compared to the theoretical model provided by MRICalc.

This doctoral thesis deals with the analysis of ultrasound (US) video sequences. It specifically focuses on long-term tracking of the common carotid artery (CCA) in transversal section and measurement of its geometric parameters in a sequence of US images. The design and implementation of a system for automatic tracking of the artery is described in this thesis. The proposed system utilizes Viola-Jones detector and Hough transform to localize the artery in the image. Interest points are detected in the area of the artery wall. These points are then tracked using optical flow. The proposed system comprises a number of innovative methods which allow to perform accurate long-term measurement of parameters of CCA and store the results. A novel mathematical model describing the movement of CCA in transversal section during a cardiac cycle is defined afterwards taking the influence of breathing into consideration. A number of artificial sequences of US images based on this model have been created. These sequences were consequently used to evaluate the accuracy of the proposed system in terms of measuring the parameters of CCA. The sequences are unique because of their length which makes them suitable for evaluation of tracking accuracy even in long video sequences.

An influence of variations in human genome is perceptible at a first glance on human itself to see differences between the individuals and entire populations. Also, behavior or probability of certain diseases are influenced in large way by differences at genome's level. This work presents methods for detecting variations in the human genome that were developed after an arose of the second-generation sequencing technologies. A new tool that combines read pair and split read methods, with information about a depth of coverage was also designed and implemented. The tool was tested on simulated and real data and compared with a reference outputs.

This master's thesis is focused on knowledge discovery from databases, especially on methods of mining sequential patterns. Individual methods of mining sequential patterns are described in detail. Further, this work deals with extending the platform Microsoft SQL Server Analysis Services of new mining algorithms. In the practical part of this thesis, plugins for mining sequential patterns are implemented into MS SQL Server. In the last part, these algorithms are compared on different data sets.

Fyzikálně přijatelné osvětlení v reálném čase je často dosaženo použitím aproximací. Současné metody často aproximují globální osvětlení v prostoru obrazu s využitím schopností moderních grafických karet. Dva techniky z této kategorie, screen-space ambient occlusion a screen-space directional occlusion jsou popsány detailněji v této práci. Screen-space directional occlusion je zobecněná verze screen-space ambient occlusion s podporou jednoho difúzního odrazu a závislostí na směrové informaci světla. Hlavním cílem projektu bylo experimentování s těmito metodami. Pro uniformní distribuci náhodných vzorek pro obě metody byla použita Halton sekvence. Pro potlačení šumu je použita bilaterální filtrace, která bere do úvahy geometrické vlastnosti scény. Metody jsou dál zrychleny použitím nižších rozlišení pro výpočet. Rekonstrukce výsledků do původní velikosti pro vytvoření konečného obrazu je realizována pomoci joint bilateral upsamplingu. Kromě metod globálního osvětlení byly v práci použity aj metody pro mapování stínů a HDR osvětlení.

The task of this thesis is to study the subject of perfusion analysis based on dynamic imaging with T2/T2* contrast. The focus was on the acquisition commonly used for DSC-MRI and especially in the acquisition pulse sequences that use images with different echo time, so called Multi-echo sequence. Principles of dynamic measurement by magnetic resonance imaging, the role of contrast agents and their influence on the relaxation times are described. It also describes the problems perfusion analysis, measurement and mathematical modeling parameters entering to the convolution dependency for getting perfusion parametersIn the experimental part is developed automatic algorithm to gain curves relaxation time T2 *. Next, the synthetic data are created and tested robustness estimate perfusion parameters against noise. In the next phase of work there are compared real scanned objects with using a conversion with T2 * and free of T2*. In the last phase of work is compared influence of length of used echo times on concentration curves and after perfusion analysis influence on resulting perfusion parameters.

Mating behaviour of cockroaches is spectacular phenomenon with three different mating patterns traditionally distinguished. The most common and probably ancestral is type A - female climbing. Then it is type B - male climbing and type C - no climbing. Mating type was described in around 30 Blaberidae species. As it is the only cockroach family where all three types are present, it is an interesting model group for studying evolutionary questions. The main goal of the thesis was detail exploration and description of mating sequences in 21 Blaberidae species, 17 of which haven't been examined in this aspect before. An intrageneric diversity in mating patterns (genus Pycnoscelus) was described for the first time. Moreover, in case of P. tenebrigera, it was not possible to assign its mating pattern to any of the three traditional types. Multidimensional statistical analysis and biological interpretation of qualitative behavioural elements revealed two well separated clusters of mating sequensces. Consequently, we propose to distinguish only two types of mating pattern - ancestral type (identical with type A) and derived type. We also discussed the relationship between wing reduction and occurence of derived mating types. Evaluation of quantitative behavioural elements revealed positive correlation between...