|
|
Methods of image dithering
Pelc, Lukáš ; Křupka, Aleš (referee) ; Rajmic, Pavel (advisor)
Master’s thesis discusses methods for dithering image. The basis is the explanation of the theory of digital images, color models, color depth and color range. Followed by the dismantling of the basic dithering methods which are a thresholding method, a random and matrix diffusion. Discussed are advanced methods of dithering with error distribution, bee with best known method Floyd-Steinberg. Included is a comparison of different methods including subjective comparison using a questionnaire. Program part is JAVA applet that shows the possibility of generating images using various dithering methods.
|
|
|
Location of Internet nodes
Janoušek, Jiří ; Křupka, Aleš (referee) ; Komosný, Dan (advisor)
The aim of this thesis is to determine the geographical position of the stations on the internet using publicly available geolocation databases. The theoretical part describes different methods and aplications used for the geolocation. The next part is dedicated to the describtion of the applied databases in more details. The practical part includes the process of developing of the functions necessary to locate the stations. The conclusion consist of the evaluation of the database‘s accuracy and the comparison of applied databases.
|
|
|
Implementation of digital metronome with oversampling in VST technology
Křupka, Aleš ; Přikryl, Lubor (referee) ; Mačák, Jaromír (advisor)
This bachelor’s thesis presents solution to requirement of implementation of digital metronome in VST technology. In the beginning, there is analysis of basic characteristics of digital metronome, that helps to suggest algorithm realizing digital metronome. Algorithm is encapsulated into C++ class with appropriate interface, which is suitable for usage in different technologies of digital sound signal processing. This way encapsulated metronome is implemented in VST technology as plug-in. For this reason, thesis contains a brief introduction to VST software development kit, definitions of its basic methods and way how to do graphical user interface of VST plug-in. For realizing of function enabling choice of any sound loaded from wav file, there is a description of RIFF format, that specifies the format of saving multimedia data into drive. Using this knowledge, the function of loading from wav file is implemented. In order to adjust sampling frequency of loaded sound, thesis deals with problems of sample rate conversion and implements resampling function.
|
|
|
Modern pitch-shifting algorithms and its aplication in virtual musical instruments
Křupka, Aleš ; Balík, Miroslav (referee) ; Trzos, Michal (advisor)
This diploma thesis deals with pitch shifting methods of acoustical signals. The theoretic part of this thesis involves description of three different pitch shifting techniques, these are the method using a modulated delay line, PICOLA method and method using a phase vocoder. The first two methods represent the processing in time domain, the third method represents the processing in frequency domain. In relation with the PICOLA method, the thesis also mentions algorithms for pitch estimation. The practical part demonstrates the use of these methods. There is described a sampler virtual musical instrument based on the playback of the sounds stored in memory. In this part the particular units providing the required functionality are described. The generating of sounds is controlled by the MIDI protocol. In the sampler is implemented the PICOLA method.
|
|
|
Detection of Landscape in Images
Dufka, Zbyněk ; Křupka, Aleš (referee) ; Číka, Petr (advisor)
The target of this thesis is theoretical summary of methods, which are used for detection of objects in database of images. Next step is to develope own algorhytm for detection of landscape. Theoretical part describes methods Viola-Jones and HOG, which are used for detection of human faces and anomalies on radiographs. This analysis is concerned with segmentation method and algorhytm for data mining from images, which contain the landscape scenery. Appropriate method and its analysis could contribute to create and to implement into developement enviroment RapidMiner in the second part of thesis.
|
|
|
Isolated word recognition
Vodička, Radek ; Křupka, Aleš (referee) ; Sysel, Petr (advisor)
Main purpose of the thesis is to study the processes and methods of isolated words recognition. In the theoretical part a basic principals are explained. The practical part is about the program creating using these principles in practice. For isolated words recognition Hidden Markov Models (HMM) are used, for obtaining decision symptoms cepstral analysis is chosen.
|
|
|
Automation of Exoscopic Analysis Using Image Processing of Sedimentary Grains Acquired by Electron Microscope
Křupka, Aleš ; Křížek,, Marek (referee) ; Baroňák, Ivan (referee) ; Říha, Kamil (advisor)
This thesis deals with image analysis methods which can be exploited in exoscopic analysis of sedimentary grains, specifically for the purpose of distinguishing between geomorphologic geneses which influenced a form of sedimentary grains. The images of sedimentary grains were acquired by a scanning electron microscope. The main contribution is the proposal of multiple methods that can significantly automate the exoscopic analysis. These methods cover the automatic segmentation of grains in image, the automatic analysis of roundness of 2D grain projection and the classification of geomorphologic geneses according to the grain surface structure. In the section concerning the automatic segmentation, a segmentation method enabling an easy subsequent manual result correction was proposed. This method is based on the split-and-merge approach. The individual steps the procedure were designed to exploit specific properties of sedimentary grain images in order to obtain the best segmentation results. In the section concerning the automatic roundness analysis of 2D projection of sedimentary grains, an influence of pixel resolution on a result roundness value was evaluated. Further, a minimal number of grains, which is necessary to analyze in order to reliably compare a pair of geomorphological geneses, was investigated. For the determination of this number, a method was proposed and experimentally verified. In the section of automatic analysis of sedimentary grain surface structure, a method for classification of geomorphologic geneses was proposed. The method utilizes low-level texture features which describes individual images of sedimentary grains. A model of geomorphological genesis is constituted of a set of histograms representing occurrences of different configurations of low-level texture features. The methods proposed in the thesis were tested and evaluated based on a database, which consists of sedimentary grain samples from 4 different geomorphological geneses (eolic, glacial, slope and volcanic).
|
|
|
Automatic recognition of human hand gestures
Olejár, Adam ; Křupka, Aleš (referee) ; Číka, Petr (advisor)
This bachelor thesis is aimed at realization application detecting hand in the video from a webcam. The first section describes the pre-processing options and object detectors based on different methods. Second part of the project talks about cross-platform Java language and useful libraries for project realization. The third section is a summary realization of the assignment.
|
|
|
Classifiaction algorithms for face-based identification systems
Hegr, Vojtěch ; Křupka, Aleš (referee) ; Malach, Tobiáš (advisor)
The thesis deals with the research of classification algorithms for face-based identification. The aim is to implement algorithms into an existing system for face recognition and the evaluation of the impect of individual classifiers. According to the survey of face recognition methods the following classifiers were chosen for implementation: K - Nearest Neighbours (K-NN), Support Vector Machines (SVM) and the Neural Networks. These classification algorithms were implemented in C++ (Microsoft Visual Studio 2010) using the open source library OpenCV. Furthermore, the IFaVID database and the methodology used to test the implemented algorithms were introduced.
|
|
|
Image segmentation based on relief
Gros, Jan ; Špiřík, Jan (referee) ; Křupka, Aleš (advisor)
The aim of this labor is to introduce the technique of image segmentation by flooding relief of landscape (watershed method). There are described some methods of image segmentation and explained the basic operations of the images, from which the morphological operations are used for watershed segmentation. Part of this labor is a short passage that deals with the use of some image filters for image preprocessing. The result of previous knowledge is presentation of segmentation algorithm designed by Lee Vincent and Pierre Soille. The next section describes the algorithm implementation in Java, contents and function of each class module and implementation using RapidMiner. The last section presents the results of the segmentation with created module using the test images without and with the use of some selected filters to reduce oversegmentation and improve the resulting segmentation.
|
guest ::
RSS feed.