|
| |
|
|
Feature extraction from image data
Uher, Václav ; Beneš, Radek (referee) ; Burget, Radim (advisor)
Image processing is one area of signal analysis. This thesis is involved in feature extraction from image data and its implementation using Java programming language. The main contribution of this thesis lies in develop features extractors and their implementation in the program RapidMiner. The result is a robust tool for image analysis. The functionality of each operator is tested on mammogram images. A function model was developed for the removal of artifacts from the mammography images. The success rate of removal is comparable with other similar works. Furthermore, learning algorithms were compared on example detection of ventricle in ultrasound image.
|
|
|
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.
|
|
|
Decentralized communication tool with anonymity guarantee
Legéň, Michal ; Burget, Radim (referee) ; Malý, Jan (advisor)
Anonymity on the internet is becoming a actuall issue nowadays. There are several tools, that can be used to monitor user's activity and it can lead to lose privacy of users. The aim of this master's thesis is to describe different ways of working anonymous systems, especially the method called Onion Routing. The introduction of this work is devoted to the description of this method together with asymmetric cryptosystem RSA. The second part belongs to basics of socket programming and to the implementation of anonymous system in programming language C++. The final part is focussed on analysis of system in terms of security and time complexity. The conditions of anonymity and decentralization are accomplished. There is no presence of central server in the system and the management is handled by signalling messages.
|
|
|
Multidimensional Data Analysis and Analytic View Processing
Foltýnová, Veronika ; Burget, Radim (referee) ; Škorpil, Vladislav (advisor)
This thesis deals with the analysis and display of multidimensional data. In the theoretical part, the issue of data mining, its tasks and techniques, and a brief explanation of the terms Business Intelligence and data warehouse are presented. The issue of databases is also described in this thesis. Subsequently, the options for displaying multidimensional data are described. At the end of the theoretical part is briefly explained the problems of optical networks and especially the terms Gigabit passive optical network and its frame, because the data from the frames of this network will be displayed by an application. In the practical part, you can find creating a source database and an application to create a OLAP cube and display multidimensional data. This application is based on the theoretical knowledge of multidimensional databases and OLAP technology.
|
|
|
Hough's transform for circle detection
Kazík, Martin ; Burget, Radim (referee) ; Říha, Kamil (advisor)
The thesis is focused on the implementation of Hough transform algorithm for circle recognition. Algorithm is implemented in C++ language using open source library OpenCv. As a development environment was chosen Microsoft Visual Studio 2008. At first there is general description of classical Hough transform for line and circle recognition. Then thesis contains description of particular steps of Hough transform algorithm and description of OpenCv functions witch are used in these steps. There is a detail description of functions for converting image to grayscale, smoothing image by Gaussian filter and Canny edge detector for edge detecting in smoothed image. Efficiency and speed of algorithm is increased by using function for finding possible centers. This function using the fact that line perpendicular to the chord of circle and going thought its middle point at the same time have to cross the center of the circle. Results of particular stages of algorithm (converting to grayscale, smoothing by Gaussian filter, edge detection, creating of possible centers accumulator and drawing circles) are presented on ultrasonic image of collagen arterial substitute. In the second part of the thesis the algorithm is used for detection of artery in frames of video captured by ultrasound. There is a description of automatic method for evaluating of success of artery detection. Success of detection is analyzed by changing values of important algorithm parameters. From series of tests there are defined ideal parameters of algorithm for artery detection in the video.
|
|
|
Text data clustering algorithms
Sedláček, Josef ; Burget, Radim (referee) ; Karásek, Jan (advisor)
The thesis deals with text mining. It describes the theory of text document clustering as well as algorithms used for clustering. This theory serves as a basis for developing an application for clustering text data. The application is developed in Java programming language and contains three methods used for clustering. The user can choose which method will be used for clustering the collection of documents. The implemented methods are K medoids, BiSec K medoids, and SOM (self-organization maps). The application also includes a validation set, which was specially created for the diploma thesis and it is used for testing the algorithms. Finally, the algorithms are compared according to obtained results.
|
|
|
Optimization of network position prediction
Pospíšil, Petr ; Pfeifer, Václav (referee) ; Burget, Radim (advisor)
This work is about position prediction in network, it is focused to find Landmark closest to the Host in the network (with lowest distance vector). The algorithm is based on GNP system. In terms of GNP system simulation was selected method for mathematical part of position prediction. The method was Simplex Downhill. The designed algorithm was implemented in Java. In the first step chose Host continent by meassuring the distance vector. In next step is selected nearest part in the continent. In conclusion estimate Host its position and then closest Landmark. Results from this work is important for designing TTP protocol. The verdict is that the GNP can be used for TTP, but Landmarks must be located in uniform density.
|
|
|
Multilayer J2EE web application
Pacvoň, Stanislav ; Kacálek, Jan (referee) ; Burget, Radim (advisor)
This thesis provides compact solutions and shows process, how it is possible to implement Information system which automatically tests students projects. The use of J2EE technology is required in assignment of this thesis. Using of other technologies depends on which way of the assignment´s solution was choosen. In the part one of the thesis an option of technologies used for the system development is implemented. The reason why used application server, database server and CMS solution were chosen is given here. The choice of CMS applicatin is reasoned in more detailed way. A building tool Ant and Junit package are introduced here as well as cascade styles and other technologies used in an application. Ant was used to build a module and students projects. JUnit package is available to test classes. In the second part of the thesis the application is designed. It is showed here how to create a web module, what components the module has to contain and how to implement required function of the system with contribution of classes, library OpenCms and Java. The second part is divided into three chapters. The first shows system workflow, which defines the way of work with application according to defined role in system .The second of them is focused on the web module and its parts. It introduces application pages designed for registration, projects assignment, projects and scripts upload and navigation pages. The three chapter is aimed at a web content. It introduces a data files and HTML output pages. Other parts of the thesis are focused on the safety of the application and the way of communication with Jplag detection of plagiarism.
|
|
|
Image annotation using deep learning
Zarapina, Natalya ; Rajnoha, Martin (referee) ; Burget, Radim (advisor)
This semester thesis describes the design and implementation of the client-server program for classification and localization of certain elements which are present in provided images. This program loads a set of images and use deep learning, especially deep convolution neural network perform a classification. First part describes the architecture, basic principles of operations in convolution network and chosen machine learning algorithms for classification. Second part contains a description of created program.
|
guest ::
