National Repository of Grey Literature 112 records found  1 - 10nextend  jump to record: Search took 0.00 seconds. 
Face superresolution from image sequence
Mezina, Anzhelika ; Rajnoha, Martin (referee) ; Burget, Radim (advisor)
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.
Image segmentation methods with limited data sets
Horečný, Peter ; Kolařík, Martin (referee) ; Burget, Radim (advisor)
The goal of this thesis was to propose an image segmentation method, which is capable of effective segmentation process with small datasets. Recently published ODE neural network was used for this method, because its features should provide better generalization in case of tasks with only small datasets available. The proposed ODE-UNet network was created by combining UNet architecture with ODE neural network, while using benefits of both networks. ODE-UNet reached following results on ISBI dataset: Rand: 0,950272 and Info: 0,978061. These results are better than the ones received from UNet model, which was also tested in this thesis, but it has been proven that state of the art can not be outperformed using ODE neural networks. However, the advantages of ODE neural network over tested UNet architecture and other methods were confirmed, and there is still a room for improvement by extending this method.
Detection of anomalies in data center network traffic
Korzhasbayeva, Leila ; Uher, Václav (referee) ; Burget, Radim (advisor)
Ve velkých společnostech existuje spousta kriticky důležitých strojů pracujících bez přestávky každý den. Jednoduché Log Management řešení není vždy dostatečné k zachycení všech dat, která tečou produkčním prostředí. Ani bezpečnostní analytik není vždy schopen sledovat každý zdroj v prostředí, chytat změny v běžném provozu. Zde je bod, kde nám stroj může pomoci. Detekce anomálií v prostředí je hlavním cílem tohoto projektu. Existuje několik řešení prezentovaných a testovaných na datech ze serverů v reálném prostředí definované společnosti. Některé false positives stále se mohou objevovat, ale je to dobrá příležitost k vyřešení v budoucím výzkumu.
Plug-in for Eclipse environment
Zaytsev, Vsevolod ; Burget, Radim (referee) ; Sysel, Petr (advisor)
This bachelor’s thesis has a goal to design a new DLTK-based (Dynamic Languages Toolkit) plug-in for the Eclipse development environment. Theoretical part of the thesis engages on the architecture of the Eclipse and describes the possibility of its extension through its own plug-ins, particularly for support of the Octave script language. Practical part of the thesis describes the creation of new plug-in for the Eclipse development environment, it’s integration and activation.
Enhancement of image quality for security forces
Varga, Adam ; Galáž, Zoltán (referee) ; Burget, Radim (advisor)
This bachelor thesis deals with image quality enhancement for security forces. Image quality enhancement in this case means increasing the resolution of image data by using super-resolution techniques using models of deep convolutional neural networks. The thesis in its theoretical part describes the principles of the operation of this technique and in its practical part is presented the work with selected state-of-the-art models in the area of super-resolution.
Predictive maintenance for automated assembly machines
Janík, Vladimír ; Burget, Radim (referee) ; Mecerod, Václav (advisor)
This thesis deals with data analysis. Data obtained from automated assembly machines and their quick and well-arranged displaying in a format suitable for individual end users. In the thesis web frameworks are compared and database structure as well as final software solution is proposed. The data is loaded using the implemented programming language module. The data is further analyzed and displayed to a user through a web-based application accessible to end user from every device connected to the corporate network.
People recognition using facial images
Lindovský, Michal ; Burget, Radim (referee) ; Rajnoha, Martin (advisor)
This bachelor thesis focuses on the person recognition between several millions of people in a few seconds. As a part of my thesis is comparison of two programs which are used for recognizing faces - OpenFace and Face Recognition. Computing times of localization and face encoding are compared. The accuracy of recognition in various tests is compared as well, such as blurred image, brightness changes, age of person or usage of sunglasses. Created web application is made for recognizing people in different databases. Is possible to add or remove databases of people in the application. The application allows to subsume people into database by gender automatically or manually. Face recognition can be speeded up by using multiple processor cores.
Client Generator for Language Server Protocol
Jelínek, Dominik ; Burget, Radim (referee) ; Číka, Petr (advisor)
The Diploma thesis deals with the Microsoft Language Server Protocol. The theoretical part describes the architecture and protocol properties, the LSP implementation within the Eclipse and VS Code development environments and a procedure for creating a new plug-in in the Eclipse and VS Code. In addition, the theoretical part familiarizes with Apache Camel project and implementation of Camel Language server and Camel Language clients for extended language support. The last mention in the theory is about the Yeoman tool for scaffolding a new projects. The description of the practical part deals with properties and implementation of the created LSP clients generator for Language Server Protocol.
Application for geolocation databases
Klíma, Oldřich ; Burget, Radim (referee) ; Komosný, Dan (advisor)
The thesis deals with possibilities for more precise determination of geographical position of given IP address by combination of estimates of data obtained from geolocation databases. The first part introduces the issue on theoretical level. Possibilities of network device identification, its geographical location and principles of geolocation databases are described here. After analyzing the theoretical part of this issue, the current state of application for geolocation databases is described. The next section introduces a new application which uses original software ip2geotools as a library. Using the three implemented methods for combining results (based on average, median, and cluster analysis by K-Means algorithm), the new program allows to estimate the physical location of IP address. The app is complemented with console interface and geographic data visualization on the map. In the last part, the accuracy of computational methods is validated and a detailed statistical analysis of data obtained by performing a calculation over a set of IP addresses with known geographical location of the RIPE Atlas service is performed.
Deep neural network for supercomputer environments
Bronda, Samuel ; Kolařík, Martin (referee) ; Burget, Radim (advisor)
The main benefit of the work is the optimization of the hardware configuration for the calculation of neural networks. The theoretical part describes neural networks, deep learning frameworks and hardware options. The next part of the thesis deals with implementation of performance tests, which include application of Inception V3 and ResNet models. Network models are applied to various graphics cards and computing hardware. The output of the thesis is the implemented model of the network Inception V3, which examines the graphics cards and their performance, time-consuming calculations and their efficiency. The ResNet model is applied to a section that examines other impacts on neural network computing such as used disk, operating memory, and so on. Each practical part contains a discussion where the knowledge of the given part is explained. In the case of consumption measurement, a mismatch between the declaration by the manufacturer and the measured values was identified.

National Repository of Grey Literature : 112 records found   1 - 10nextend  jump to record:
See also: similar author names
Interested in being notified about new results for this query?
Subscribe to the RSS feed.