|
|
Image Denoising
Jurák, Martin ; Svoboda, Pavel (referee) ; Bařina, David (advisor)
Digital images are often corrupted by noise. Therefore, a lot of methods were designed for the purpose of denoising images. This paper describes and compares three of these methods: low-pass filters, bilateral filter and wavelet thresholding. Low-pass filters are linear filters applied on image by convolution. Their disadvantage is making images smooth. Bilateral filter is an extension of low-pass filters. It smooths images as well, however it preserves edges. Wavelet thresholding is a more complex method using wavelet transform for time-frequency representation of image whose coefficients are thresholded. The downside of this method is making artifacts in images. The PSNR and SSIM methods are used for measuring image quality.
|
|
|
Fractals and Their Applications in Computer Graphics
Tesař, Martin ; Čermák, Martin (referee) ; Koutný, Jiří (advisor)
First part of this bachelors thesis consists of fractal theory, Hausdorff dimension and their applications in computer graphics. In second part is choosen idea for application. It is interactive creation of flame fractals. In this section, there is defined mathematical system of iterated functions, that is the heart of flame fractals. After mathematical examination follows analysis of original algorithm for creation of flame fractals. Thesis continues with methods for image improvement and suggests new enhancements.
|
|
| |
|
|
Neural Network Based Edge Detection
Jamborová, Soňa ; Grézl, František (referee) ; Švub, Miroslav (advisor)
This work is about suggestion and implementation of the software for detection of edges in images using neurons network. It defines basic terms for this topic and focusing mainly at preperation imaging imformation for detection using nerons network. Describing and comparing different aproachings for using implemented software on synthetic and real set of images, including experiments.
|
|
|
Set of Web-Based Demonstrations for Signal Processing
Kaňok, Tomáš ; Jančík, Zdeněk (referee) ; Černocký, Jan (advisor)
The aim of this bachelor's thesis is to give a basic overview about convolutions and complex exponential functions used in signal processing. Additionally, it contains the list of existing public educationally-oriented solutions available on the Internet. Set of web-based demonstrations for signal processing is proposed, implemented and evaluated upon analyzed solutions.
|
|
|
Neural Network Based Edge Detection
Janda, Miloš ; Žák, Pavel (referee) ; Švub, Miroslav (advisor)
Aim of this thesis is description of neural network based edge detection methods that are substitute for classic methods of detection using edge operators. First chapters generally discussed the issues of image processing, edge detection and neural networks. The objective of the main part is to show process of generating synthetic images, extracting training datasets and discussing variants of suitable topologies of neural networks for purpose of edge detection. The last part of the thesis is dedicated to evaluating and measuring accuracy values of neural network.
|
|
|
Accelerated Image Resampling Library
Hamrský, Jan ; Bařina, David (referee) ; Polok, Lukáš (advisor)
This work deals with the task of image scaling using GPU paralelization. Portion of text is devoted to signal processing and his affection of whole result including measuring it's quality. Describtion of the most important methods including super-resolution is given further in the text. An important part of this thesis is library implementing choosen methods with usage of paralelization on graphic chip. Achieved results of paralelization are demonstrated on set of speed tests.
|
|
|
Recognition of Poses and Gestures
Jiřík, Leoš ; Hradiš, Michal (referee) ; Zemčík, Pavel (advisor)
This thesis inquires the existing methods on the field of image recognition with regards to gesture recognition. Some methods have been chosen for deeper study and these are to be discussed later on. The second part goes in for the concenpt of an algorithm that would be able of robust gesture recognition based on data acquired within the AMI and M4 projects. A new ways to achieve precise information on participants position are suggested along with dynamic data processing approaches toward recognition. As an alternative, recognition using Gaussian Mixture Models and periodicity analysis are brought in. The gesture class in focus are speech supporting gestures. The last part demonstrates the results and discusses future work.
|
|
|
Design of a New Method for Stereovision
Kopečný, Josef ; Drahanský, Martin (referee) ; Orság, Filip (advisor)
This thesis covers with the problems of photogrammetry. It describes the instruments, theoretical background and procedures of acquiring, preprocessing, segmentation of input images and of the depth map calculating. The main content of this thesis is the description of the new method of stereovision. Its algorithm, implementation and evaluation of experiments. The covered method belongs to correlation based methods. The main emphasis lies in the segmentation, which supports the depth map calculation.
|
|
|
Image Database Query by Example
Dobrotka, Matúš ; Hradiš, Michal (referee) ; Veľas, Martin (advisor)
This thesis deals with content-based image retrieval. The objective of the thesis is to develop an application, which will compare different approaches of image retrieval. First basic approach consists of keypoints detection, local features extraction and creating a visual vocabulary by clustering algorithm - k-means. Using this visual vocabulary is computed histogram of occurrence count of visual words - Bag of Words (BoW), which globally represents an image. After applying an appropriate metrics, it follows finding similar images. Second approach uses deep convolutional neural networks (DCNN) to extract feature vectors. These vectors are used to create a visual vocabulary, which is used to calculate BoW. Next procedure is then similar to the first approach. Third approach uses extracted vectors from DCNN as BoW vectors. It is followed by applying an appropriate metrics and finding similar images. The conclusion describes mentioned approaches, experiments and the final evaluation.
|
guest ::
