|
|
Generating Faces with Generative Adversarial Networks
Konečný, Daniel ; Herout, Adam (referee) ; Kolář, Martin (advisor)
Cílem této práce je generování barevných obrázků obličejů z náhodně určených vysokodimenzionálních vektorů pomocí generativních neuronových sítí. Dále se zabývá analýzou vstupních vektorů na základě příznaků obličejů z nich vygenerovaných. Je provedena implementace generativní neuronové sítě pro generování obrázků ručně psaných číslic, poté dalších dvou sítí pro generování obrázků obličejů. Vygenerované obrázky zobrazují věrohodně vypadající obličeje, lidské oko je však dokáže odlišit od fotek reálných osob. Analýza jednotlivých dimenzí vektorů je provedena pomocí Studentova t-testu. Dále jsou vstupní vektory promítnuty do podprostorů pomocí lineární diskriminační analýzy a jsou nalezeny rozdělovací hranice mezi třídami příznaků. Analýza generovaných dat dokazuje, že ovlivněním vstupního vektoru je možné docílit generování obrázku obličeje s požadovanými příznaky s pravděpodobností až 80 %. Hlavním výsledkem této práce je model generativní neuronové sítě určené pro generování obrázků obličejů. Dalším přínosem je nástroj pro generování obrázků obličejů na základě vybraných příznaků.
|
|
|
Integrace Sociálních sítí
Mašíček, Viktor ; Tykal, Jaroslav (advisor) ; Skopal, Tomáš (referee)
Social networks are the current phenomenon, and their integration begins to gain importance. Basic idea is to pair identical pieces of information stored in various social networks and to detect inconsistencies between them. The most important data that need to be integrated are user profi les and lists of contacts. In our work, we propose the integration of both the pro files and lists of contacts, and even groups of users that could be created in social networks. Implementation is not part of the work. However the proposal suggests the creation of Main social network in form of a web application, that brokers the integration to end users. From the perspective of users it is bene cial to display data from all social networks in one place and automate detection of di erences. User's data could be used for commercial purposes, of course, within legal limits. From this perspective, the biggest contribution of Main social network is a social graph. It consists of various social graphs of social networks. Additionally it would contain information about membership of users in social networks. The proposal consists of three main parts: main processes of the Main social network, its data model and means of gathering information from different networks. The design of data model was partially inspired by existing...
|
|
|
XSLT Benchmarking
Mašíček, Viktor ; Holubová, Irena (advisor) ; Lokoč, Jakub (referee)
The main goal of this work was to create an XSLT Benchmark, to compare available XSLT processors. At first, we determined main criteria of XSLT processors (price, correctness, speed, memory usage, support, OS and UX), which we discussed. Next, we summarized existing XSLT processors, described individual types of processors (program, library and browser) and measured criteria price, support, OS} and UX. We had to create appropriate test environment to measure criteria correctness, speed and memory usage. Created program XSLT Benchmarking is one of the main benefits of this work. The program also includes tests. We created tests based on 5787 downloaded XSLT files. Tests were created based on the analysis of these files. Firstly, we researched common features of XSLT files (used elements, used XSLT versions, output format etc.). Secondly, we researched focuses of their usages. Next big benefit of this work is a summary of results of tests from different views. We discussed other criteria and features of tested processors. Finally, we summarized possible extensions of our program and also of our analysis.
|
|
|
Generating Tree Structures for Testing of Information Systems
Rozsíval, Michal ; Hruška, Martin (referee) ; Smrčka, Aleš (advisor)
The work aims to create a tool for automated testing of information systems. It creates messages similar in structure to those in the communication of existing systems. The program reads provided communication record according to configuration and saves the individual messages in a uniform form. It splits the saved messages into groups and abstracts them into a suitable form for a subsequent generation of new random test messages based on a combinatorial testing with Pair-Wise coverage. The tool supports communication using the REST API and OPC UA protocols and structured data in XML and JSON . The program was tested by processing real communication records.
|
|
|
Generating Faces with Generative Adversarial Networks
Konečný, Daniel ; Herout, Adam (referee) ; Kolář, Martin (advisor)
Cílem této práce je generování barevných obrázků obličejů z náhodně určených vysokodimenzionálních vektorů pomocí generativních neuronových sítí. Dále se zabývá analýzou vstupních vektorů na základě příznaků obličejů z nich vygenerovaných. Je provedena implementace generativní neuronové sítě pro generování obrázků ručně psaných číslic, poté dalších dvou sítí pro generování obrázků obličejů. Vygenerované obrázky zobrazují věrohodně vypadající obličeje, lidské oko je však dokáže odlišit od fotek reálných osob. Analýza jednotlivých dimenzí vektorů je provedena pomocí Studentova t-testu. Dále jsou vstupní vektory promítnuty do podprostorů pomocí lineární diskriminační analýzy a jsou nalezeny rozdělovací hranice mezi třídami příznaků. Analýza generovaných dat dokazuje, že ovlivněním vstupního vektoru je možné docílit generování obrázku obličeje s požadovanými příznaky s pravděpodobností až 80 %. Hlavním výsledkem této práce je model generativní neuronové sítě určené pro generování obrázků obličejů. Dalším přínosem je nástroj pro generování obrázků obličejů na základě vybraných příznaků.
|
|
|
Graphics Intro 64kB Using OpenGL
Minařík, Antonín ; Matýšek, Michal (referee) ; Herout, Adam (advisor)
This thesis deals with creating a graphics intro, which's size has to be below 64~kB. Described and used techniques includes: Phong reflection model, fog, skybox, generating textures from noise and shadow mapping. Intro is placed in a city and techniques of generating elements of the city are described. In addition, there are described methods for reducing file size and system for camera animation.
|
|
|
Image data shape analysis
Kylián, Jakub ; Harabiš, Vratislav (referee) ; Chmelík, Jiří (advisor)
Bachelor thesis is focused on shape analysis of image data. This thesis clarifies usage of methods, techniques and procedures that lead to such analysis. The content of this thesis is divided into three chapters – theory, analysis solution and conclusion. In the chapter theory, methods and general theory of the topic are introduced. The rule is, that every method used in subsequent sections is explained in detail, but this doesn't necessarily mean that it applies in reverse. Next chapter, following up the theory section is analysis solution. In this section, a problem is presented. This problem is then, with knowledge presented in chapter theory solved. The solution consists of many processes and preparations that are also explained in detail in this chapter.
|
|
|
Image data shape analysis
Kylián, Jakub ; Harabiš, Vratislav (referee) ; Chmelík, Jiří (advisor)
Bachelor thesis is focused on shape analysis of image data. This thesis clarifies usage of methods, techniques and procedures that lead to such analysis. The content of this thesis is divided into three chapters – theory, analysis solution and conclusion. In the chapter theory, methods and general theory of the topic are introduced. The rule is, that every method used in subsequent sections is explained in detail, but this doesn't necessarily mean that it applies in reverse. Next chapter, following up the theory section is analysis solution. In this section, a problem is presented. This problem is then, with knowledge presented in chapter theory solved. The solution consists of many processes and preparations that are also explained in detail in this chapter.
|
|
|
XSLT Benchmarking
Mašíček, Viktor ; Holubová, Irena (advisor) ; Lokoč, Jakub (referee)
The main goal of this work was to create an XSLT Benchmark, to compare available XSLT processors. At first, we determined main criteria of XSLT processors (price, correctness, speed, memory usage, support, OS and UX), which we discussed. Next, we summarized existing XSLT processors, described individual types of processors (program, library and browser) and measured criteria price, support, OS} and UX. We had to create appropriate test environment to measure criteria correctness, speed and memory usage. Created program XSLT Benchmarking is one of the main benefits of this work. The program also includes tests. We created tests based on 5787 downloaded XSLT files. Tests were created based on the analysis of these files. Firstly, we researched common features of XSLT files (used elements, used XSLT versions, output format etc.). Secondly, we researched focuses of their usages. Next big benefit of this work is a summary of results of tests from different views. We discussed other criteria and features of tested processors. Finally, we summarized possible extensions of our program and also of our analysis.
|
|
|
Integrace Sociálních sítí
Mašíček, Viktor ; Skopal, Tomáš (referee) ; Tykal, Jaroslav (advisor)
Social networks are the current phenomenon, and their integration begins to gain importance. Basic idea is to pair identical pieces of information stored in various social networks and to detect inconsistencies between them. The most important data that need to be integrated are user profi les and lists of contacts. In our work, we propose the integration of both the pro files and lists of contacts, and even groups of users that could be created in social networks. Implementation is not part of the work. However the proposal suggests the creation of Main social network in form of a web application, that brokers the integration to end users. From the perspective of users it is bene cial to display data from all social networks in one place and automate detection of di erences. User's data could be used for commercial purposes, of course, within legal limits. From this perspective, the biggest contribution of Main social network is a social graph. It consists of various social graphs of social networks. Additionally it would contain information about membership of users in social networks. The proposal consists of three main parts: main processes of the Main social network, its data model and means of gathering information from different networks. The design of data model was partially inspired by existing...
|
guest ::
