|
|
Image quality analysis using Fourier transform
Tkadlecová, Markéta ; Druckmüller, Miloslav (referee) ; Hoderová, Jana (advisor)
This thesis deals with two-dimensional Fourier transform and its use in digital image quality assessment. An algorithm based on amplitude spectra is introduced and tested on different sets of images. Its possible use and disadvantages are described. For understanding the basics of the algorithm the fundamental mathematical theory is included. Mainly the properties of amplitude spectra are explained. Next, the theory of digital images and their characteristics, which can affect their quality, is described. For testing the quality of the image the demonstrative program has been developed.
|
|
|
System for Import of Photos
Pučálka, Martin ; Mlích, Jozef (referee) ; Zemčík, Pavel (advisor)
The goal of this thesis is design and implementation of stand-alone program for import of photos. Program can find already imported photos in computer and skip them during next import. Searching for identic photos is based on comparing metadata. Thanks to this way of comparasion, aplication doesn't need to load and compare image data and searching can be faster. Implemented were also functions for separating, renaming and adding metatada to photos.
|
|
|
Fear Eats the Soul
Spalajković, Tamara ; Marković, Nikola (referee) ; Mazanec, Martin (advisor)
For my master thesis I present a video installation named Orlando: Fear Eats the Soul. The project aims to explore the tension created by performative disrupting of the complex relationship between humans and digital images. Contemporary modes of our (human) interaction with digital media challenge the divide between digital and “real.” The video and the installation deal with the potential of performative addressing of this divide through a fictional narrative, utilizing the formal characteristics of a digital camera (apparatus) as a gatekeeping instrument. In this documentation I elaborate on the theoretical and contextual foundations of the project and offer insight into the methods used in the production of the video – the central piece of the installation.
|
|
|
System for Management and Selection of Photos
Blažek, Tomáš ; Lysek, Tomáš (referee) ; Zemčík, Pavel (advisor)
The goal of this bachelor thesis was to create a system for management and selection photos, that should allow users to effectively search in a large number of photos. Criteria of selection include search by elements occurring in the photo, address of place and date of creation photo. Final result is the system implemented in Python language using open source neural network implemented in C language.
|
|
|
Thermal image processing using the superresolution technique
Petrásek, Daniel ; Číka, Petr (referee) ; Mekyska, Jiří (advisor)
Thesis deals with problematic of raising digital image spacial resolution, mainly thermal image. There are mentioned methods of interpolation, panorama and super-resolution. Main topic of this thesis is super-resolution which is detailly described during the thesis. Finally there is a description of algorithm implementation and problems that may occur during the implemetation.
|
|
|
Library for Efficient Video Capture in 3D Application
Pospíšil, Petr ; Navrátil, Jan (referee) ; Havel, Jiří (advisor)
This thesis deals with library for recording video in the background of 3D application. A library is designed to work under the Microsoft Windows and Linux operation systems. It records image and also sound. Image recording is supported in OpenGL, Direct3D9, Direct3D10 and Direct3D11. To reduce video data size, library supports image compression using MJPG codec. Audio is recorded by WaveForm audio, Windows Core Audio or ALSA. Recorded sound is for whole operation system. A library is able to record up to two audio streams to accommodate possible microphone input. It can mix audio data together if needed. Output data are then written into AVI file. It is possible to write own text information as overlay that is rendered as part of application screen output.
|
|
|
Applications supporting lectures on colour models
Khaladzinski, Kiryl ; Záviška, Pavel (referee) ; Rajmic, Pavel (advisor)
The aim of this bachelor thesis is to create Web applications that show the possibilities of working with different color models in real examples shows principles of digital images creation and the possibility of processing digital image data. Theoretical part devoted to the basic concept in color theory and the basis of raster images. The practical part is the design of four applications and their creation. The first of the applets shows the principle of mixing colors in different color models, the second on the example shows the basis of the index representation of the image, the third shows the methods of translating the color image to grayscale and the last applet is used to translate grayscale image to color image.
|
|
|
Applications supporting lectures on colour models
Khaladzinski, Kiryl ; Záviška, Pavel (referee) ; Rajmic, Pavel (advisor)
The aim of this bachelor thesis is to create Web applications that show the possibilities of working with different color models in real examples shows principles of digital images creation and the possibility of processing digital image data. Theoretical part devoted to the basic concept in color theory and the basis of raster images. The practical part is the design of four applications and their creation. The first of the applets shows the principle of mixing colors in different color models, the second on the example shows the basis of the index representation of the image, the third shows the methods of translating the color image to grayscale and the last applet is used to translate grayscale image to color image.
|
|
| |
|
|
Physical aspects of digital image and object detection using convolutional neural networsk
ŠTINDLOVÁ, Lucie
The thesis is focused on computer vision and the comparison of trained deep learning models. In the theoretical part, a detailed overview of the physical properties of the visible electromagnetic spectrum and the principles of the digital image, including it, is processed. This is followed by a review of image processing methods, where conventional methods and then convolutional neural networks are briefly characterized. The practical part is focused on creating a suitable dataset with annotations, which is further applied for training selected models. The variability and accuracy of the obtained results is analyzed from the point of view of the selected evaluation metrics, as well as based on the experimental determination of input parameters for training.
|
guest ::
