|
ASL Fingerspelling Recognition Using Slow Feature Analysis
Winkler, Martin ; Hradiš, Michal (referee) ; Burget, Lukáš (advisor)
Táto práca popisuje proces testovania slow feature analysis ako metódy, ktorá extrahuje robustné črty z komplexných obrazových dát americkej znakovej reči. Za účelom testovania bol vytvorený systém v programovacom jazyku python, ktorý zjednodušuje testovanie a ponúka bohatú škálu meniteľných parametrov aby umožnil užívateľovi rôzne testy za účelom zistenia nakoľko použiteľná je táto metóda na klasifikáciu a rozpoznávanie gest rúk. Teoretická časť predstaví slow feature analysis, diskutuje o štruktúre systému a popisuje dáta na ktorých bude metóda pozorovaná. V praktickej časti je metóda podrobená analýze úspešnosti na videných a nevidených rečníkoch, jej schopnosť adaptovať sa na vyšší počet gest a zaujímavé formátovanie dát v pokuse vylepšiť jej úspešnosť.
|
|
Quality Analysis of Electronic Dictionaries Transformation
Stehlíková, Petra ; Škoda, Petr (referee) ; Kouřil, Jan (advisor)
The bachelor's thesis deals with electronic dictionaries, their formats and quality analysis of their conversions. The thesis describes Lexical Markup Framework format in detail. It also discusses the capabilities of advanced algorithms such as LSA for conversion quality analysis and the tools that can be used for the analysis. Based on this theoretical knowledge the scripts in Python language were created to analyze dictionaries in Lexical Markup Framework format.
|
|
Methods of Document Summarization on the Web
Belica, Michal ; Očenášek, Pavel (referee) ; Bartík, Vladimír (advisor)
The work deals with automatic summarization of documents in HTML format. As a language of web documents, Czech language has been chosen. The project is focused on algorithms of text summarization. The work also includes document preprocessing for summarization and conversion of text into representation suitable for summarization algorithms. General text mining is also briefly discussed but the project is mainly focused on the automatic document summarization. Two simple summarization algorithms are introduced. Then, the main attention is paid to an advanced algorithm that uses latent semantic analysis. Result of the work is a design and implementation of summarization module for Python language. Final part of the work contains evaluation of summaries generated by implemented summarization methods and their subjective comparison of the author.
|
|
Semantic Similarity of Texts
Bradáč, Václav ; Otrusina, Lubomír (referee) ; Smrž, Pavel (advisor)
This paper deals with the determination of semantic similarity texts, focusing on scalability. Part of treatment is a theoretical overview of the tools to implement the system on test data. Tested corpus contains expert articles in the English language. The aim is to analyze these articles, modified to facilitate the analysis of their semantic analogues. One of the most utilized tools is a representation of data in a vector space model.
|
|
Multipoint identification of position and orientation of object
Řičánek, Dominik ; Ligocki, Adam (referee) ; Burian, František (advisor)
The goal of this paper is to find a good method to determine the pose of two, mutually rotated, objects and to try and implement it first in C++ without the usage of any external libraries and then in Kuka Robot Language (KRL). First we are going to look at two different approaches to solving this problem: The Iterative Closest Point algorithm (ICP) and the Kabsch Algorithm. From them one is going to be chosen and a program will be build around it. Following its implementation, the algorithm’s precision is going to be tested. Finally KRL will be briefly introduced and the various problems involving transition of the algorithm from C++ to KRL will be talked about.
|
|
Separation of dynamic and static structures in a series of images
Gebrtová, Karolína ; Kosová, Petra (referee) ; Rajmic, Pavel (advisor)
This bachelor thesis is focused on the separation of static and dynamic structures of video. While the major part of the video background remains static, a few moving particles can be observed. Such video can be represented by a low-rank and a sparse component. Using a low-rank structure, the background can be separated by applying either the median filter or the dynamic mode decomposition. Furthermore, the thesis includes the robust principal component analysis which can be perceived as an optimization problem. In addition, the thesis is enhanced by result visualization methods.
|
|
Deconvolution in perfusion imaging
Líbal, Marek ; Havlíček, Martin (referee) ; Bartoš, Michal (advisor)
The purpose of this study is to introduce the methods of the deconvolution and to programme some of them. For the simulation, the tissue homogeneity model and the model of arterial input fiction were used. These models were engaged as the test procedures with the aim of verify the functionality and utility of the Wiener filter, the Lucy-Richardson algorithm and the Singular value decomposition.
|
|
Decomposition of video-sequences into components with different dynamics
Gebrtová, Karolína ; Druckmüller, Miloslav (referee) ; Rajmic, Pavel (advisor)
The thesis is focused on the decomposition of video sequences, primarily on background and dynamic component separation, where the background remains the same and only small parts are in motion. Such a video is represented by a low-rank and sparse component. Thanks to the low-rank structure, the background can be separated using a median filter and dynamic mode decomposition. Furthermore, the robust principal component analysis, formulated as an optimization problem and its non-convex variant, will be employed. Also mentioned will be the multiresolution DMD, which is capable of decomposing the dynamic component based on its velocity.
|
|
Numerical methods in image processing for applications in jewellery industry
Petrla, Martin ; Hnětynková, Iveta (advisor) ; Plešinger, Martin (referee)
Presented thesis deals with a problem from the field of image processing for application in multiple scanning of jewelery stones. The aim is to develop a method for preprocessing and subsequent mathematical registration of images in order to increase the effectivity and reliability of the output quality control. For these purposes the thesis summerizes mathematical definition of digital image as well as theoretical base of image registration. It proposes a method adjusting every single image to increase effectivity of its subsequent processing. One image for every evaluated gemstone is generated using image registration. The method is implementated in the MATLAB environment. Powered by TCPDF (www.tcpdf.org)
|
|
Separation of dynamic and static structures in a series of images
Gebrtová, Karolína ; Kosová, Petra (referee) ; Rajmic, Pavel (advisor)
This bachelor thesis is focused on the separation of static and dynamic structures of video. While the major part of the video background remains static, a few moving particles can be observed. Such video can be represented by a low-rank and a sparse component. Using a low-rank structure, the background can be separated by applying either the median filter or the dynamic mode decomposition. Furthermore, the thesis includes the robust principal component analysis which can be perceived as an optimization problem. In addition, the thesis is enhanced by result visualization methods.
|