|
|
Echo suppressor
Kratochvíl, Pavel ; Smékal, Zdeněk (referee) ; Sysel, Petr (advisor)
In the communication networks a common problem is a returned copy of an original signal that goes back through the network to the sender, disturbing the communication. This problem is attacked using Echo Cancellors that should comply with the specifications of ITU-T organization. Algorithms suitable for cancellors should be tested under specified conditions, then a decision should be taken regarding their deployment. This work deals with basic Least Mean Squares and Normalized Least Mean Squares algorithms.
|
|
|
Retinal image processing using wavelet transform
Portyš, Jakub ; Kolář, Radim (referee) ; Taševský, Pavel (advisor)
Work is focused on usage wavelet transform in diagnostic of retinae illness. Wavelet transform enables decomposition of eye background pictures. With the following segmentation by force of thresholding it leads to lucidity of picture and simpler diagnostics of morphological and anatomical changes. Part of work is also familiarization with wavelet transform and mother's wavelet family. Marginally is in work analysed picture segmentation according to RGB coloured model, picture filtration and thresholding. In opening chapters are mentioned essential piece of knowledge from anatomy, physiology and pathology.
|
|
|
Wavelet Wiener filter of ECG signals
Janů, Joshua ; Kozumplík, Jiří (referee) ; Smital, Lukáš (advisor)
The thesis focuses on the use of wavelet wiener filtration to remove muscular interference from ECG signals. As part of it, a filter has been implemented in the MATLAB programming environment. The main part of the thesis deals with the optimization of numerical parameters of the proposed filter. The results of the filtration are compared with the results reported by other authors.
|
|
|
Segmentation of ECG signals based on their quality
Zobačová, Barbora ; Maršánová, Lucie (referee) ; Vítek, Martin (advisor)
This semestral thesis deals with methods for continuous estimation of the quality of the ECG signal. The theoretical part includes the functional anatomy of the heart, the basics of electrocardiography, the types of noise that can be found in the ECG records, and a description of several methods for the continuous estimation of the ECG signal quality. Next here are some approaches to segmenting ECG signals based on their quality. The practical part deals with the implementation of two methods. The first method is the SNR estimation method based on the Wiener filter. The second method is the method of segmentation of ECG signals based on their quality. Both methods were tested on artificial and real signals.
|
|
|
Restoration of optical coherence tomography image data
Smékal, Ondřej ; Odstrčilík, Jan (referee) ; Jan, Jiří (advisor)
Restoration of image data has become an essential part of the processing of medical images obtained by any system. The same applies in the case of optical coherence tomography. The aim of this work is to study the first restoration methods. Second, the description of the data representation from optical coherence tomography and subsequent discussions that restoration methods based on deconvolution would potentially find application in processing of Optical coherence tomography. Finally, the third to create a program solution of the OCT data restoration process in MATLAB environment and followed by discussion of effectiveness of the presented solutions.
|
|
|
Suppresion of distortion in iris images
Jalůvková, Lenka ; Štohanzlová, Petra (referee) ; Kolář, Radim (advisor)
This master`s thesis is focused on a suppression of a distorsion in iris images. The aim of this work is to study and describe existing degradation methods (1D motion blur, uniform 2D motion blur, Gaussian blur, atmospheric turbulence blur, and out of focus blur). Furthermore, these methods are implemented and tested on a set of images. Then, we designed methods for suppression of these distorsions - inverse filtration, Wiener filtration and iterative deconvolution. All of these methods were tested and evaluated. Based on the experimental results, we can conclude that the Wiener-filter restoration is the most accurate approach from our test set. It achieves the best results in both normal and iterative mode.
|
|
|
Sensor Security - Verification of Image Authenticity
Juráček, Ivo ; Španěl, Michal (referee) ; Zemčík, Pavel (advisor)
Diploma thesis is about image sensor security. Goal of the thesis was study data integrity gained from the image sensors. Proposed method is about source camera identification from noise characteristics in image sensors. Research was about influence of denoising algorithms applied to digital images, which was acquired from 15 different image sensors. Finally the statistical evaluation had been done from computed results.
|
|
|
Wavelet Wiener filter of ECG signals
Sedláčková, Eva ; Odstrčilík, Jan (referee) ; Smital, Lukáš (advisor)
The aim of this work is introduction with method of filtering the ECG signals using wavelet transformation and use of this method for filtering of signal disturbed with myopotencials. The work deals with general properties and with genesis of ECG signals and describes ECG curve. Next part of work is focused on wavelet transformation, types of wavelet transformation and different methods calculation thresholds and thresholding. Design part of work is focused on design Wiener filter for remove myopotencials from ECG signals and finding optimal parameters of this filter using optimization algorithm. For optimization is used simplex method. Discovered optimal parameters are assessed on CSE and MIT-BIH Arrhythmia database and compared with results of other authors.
|
|
|
Automatic Generating of Subtitles by Speech Recognizer
Csintalan, György ; Plchot, Oldřich (referee) ; Schwarz, Petr (advisor)
This bachelor thesis describes developing an application for automatic generation of subtitles for films using BSAPI (Brno Speech Application Interface). At first the reader is guided to the problematics of this task and the aim of this work is described. In the next section the speech recognition API (BSAPI) is described from a theoretical point of wiev. After this, the next section is about extracting voice channel from video. The next chapter describes the implementation of the application. Further, experiments in different situations are described and possible improvements are discussed in order to achieve better outputs, for example speech enhancement by Wiener filter. In the conclusion are discussed achieved results and experiments.
|
|
|
Wavelet Based Filtering of Electrocardiograms
Smital, Lukáš ; Smékal, Zdeněk (referee) ; Halámek, Josef (referee) ; Kozumplík, Jiří (advisor)
This dissertation deals with possibilities of using wavelet transforms for elimination of broadband muscle noise in ECG signals. In this work, the characteristics of ECG signals and particularly the most frequently occurring type of interference are discussed firstly. The theory of wavelet transforms is also introduced and followed by design of the simple wavelet filter and the more sophisticated version with wiener filtering of wavelet coefficients. Next part is devoted to the design of our filter, which is based on wavelet wiener filtering and is complemented by algorithms that ensure full adaptability of its parameters when the properties of the input signal are changing. Suitable parameters of the proposed system are searched automatically and the algorithm is tested on the complete standard electrocardiograms database CSE, where it achieves significantly better results than other published methods.
|
guest ::
