|
|
Enhancement of image quality for security forces
Varga, Adam ; Galáž, Zoltán (oponent) ; Burget, Radim (vedoucí práce)
This bachelor thesis deals with image quality enhancement for security forces. Image quality enhancement in this case means increasing the resolution of image data by using super-resolution techniques using models of deep convolutional neural networks. The thesis in its theoretical part describes the principles of the operation of this technique and in its practical part is presented the work with selected state-of-the-art models in the area of super-resolution.
|
|
|
Aplikace waveletové transformace v software Mathematica a Sage
Novotný, Radek ; Trzos, Michal (oponent) ; Rajmic, Pavel (vedoucí práce)
Diplomová práce se zabývá zpracováním obrazu pomocí vlnkové transformace. Jsou prozkoumány její možnost využití při kompresi obrazu a kompenzaci generovaného šumu v obraze. Práce obsahuje rozbor problematiky jednotlivých druhů vlnkových transformací CWT, DWT, DTWT, 2D DWT a jejich realizace. Dále osvětluje pojem mateřská vlnka a zkoumá některé druhy vlnek, způsoby a účel prahování a okrajově se dotýká standardu JPEG2000. V programech Mathematica a Sage byly navrženy algoritmy ke kompresi obrazu a kompenzaci šumu využívající předchozích poznatků o WT. Závěr práce obsahuje porovnání obou programů a výsledky algoritmů.
|
|
|
Methods for enhancing quality of digital images
Svoboda, Radovan ; Janáková, Ilona (oponent) ; Petyovský, Petr (vedoucí práce)
With arrival of affordable digital technology we are increasingly coming into contact with digital images. Cameras are no longer dedicated devices, but part of almost every mobile phone, PDA and laptop. This paper discusses methods for enhancing quality of digital images with focus on removing noise, creating high dynamic range (HDR) images and extending depth of field (DOF). It contains familiarization with technical means for acquiring digital image, explains origin of image noise. Further attention is drawn to HDR, from explaining the term, physical basis, difference between HDR sensing and HDR displaying, to survey and historical development of methods dealing with creating HDR images. The next part is explaining DOF when displaying, physical basis of this phenomenon and review of methods used for DOF extension. The paper mentions problem of acquiring images needed for solving given tasks and designs method for acquiring images. Using it a database of test images for each task was created. Part of the paper also deals with design of a program, that implements discussed methods, for solving the given tasks. With help of proposed class imgmap, quality of output images is improved, by modifying maps of input images. The paper describes methods, improvements, means of setting parameters and their effects on algorithms and control of program using proposed GUI. Finally, comparison with free software for extending DOF takes place. The proposed software provides at least comparable results, the correct setting of parameters for specific cases allows to achieve better properties of the resulting image. Time requirements of image processing are worse because designed software was not optimised.
|
|
|
Enhancement of image quality for security forces
Varga, Adam ; Galáž, Zoltán (oponent) ; Burget, Radim (vedoucí práce)
This bachelor thesis deals with image quality enhancement for security forces. Image quality enhancement in this case means increasing the resolution of image data by using super-resolution techniques using models of deep convolutional neural networks. The thesis in its theoretical part describes the principles of the operation of this technique and in its practical part is presented the work with selected state-of-the-art models in the area of super-resolution.
|
|
|
Aplikace waveletové transformace v software Mathematica a Sage
Novotný, Radek ; Trzos, Michal (oponent) ; Rajmic, Pavel (vedoucí práce)
Diplomová práce se zabývá zpracováním obrazu pomocí vlnkové transformace. Jsou prozkoumány její možnost využití při kompresi obrazu a kompenzaci generovaného šumu v obraze. Práce obsahuje rozbor problematiky jednotlivých druhů vlnkových transformací CWT, DWT, DTWT, 2D DWT a jejich realizace. Dále osvětluje pojem mateřská vlnka a zkoumá některé druhy vlnek, způsoby a účel prahování a okrajově se dotýká standardu JPEG2000. V programech Mathematica a Sage byly navrženy algoritmy ke kompresi obrazu a kompenzaci šumu využívající předchozích poznatků o WT. Závěr práce obsahuje porovnání obou programů a výsledky algoritmů.
|
|
|
Aplikace waveletové transformace v software Mathematica a Sage
Novotný, Radek ; Trzos, Michal (oponent) ; Rajmic, Pavel (vedoucí práce)
Diplomová práce se zabývá zpracováním obrazu pomocí vlnkové transformace. Jsou prozkoumány její možnost využití při kompresi obrazu a kompenzaci generovaného šumu v obraze. Práce obsahuje rozbor problematiky jednotlivých druhů vlnkových transformací CWT, DWT, DTWT, 2D DWT a jejich realizace. Dále osvětluje pojem mateřská vlnka a zkoumá některé druhy vlnek, způsoby a účel prahování a okrajově se dotýká standardu JPEG2000. V programech Mathematica a Sage byly navrženy algoritmy ke kompresi obrazu a kompenzaci šumu využívající předchozích poznatků o WT. Závěr práce obsahuje porovnání obou programů a výsledky algoritmů.
|
|
|
Methods for enhancing quality of digital images
Svoboda, Radovan ; Janáková, Ilona (oponent) ; Petyovský, Petr (vedoucí práce)
With arrival of affordable digital technology we are increasingly coming into contact with digital images. Cameras are no longer dedicated devices, but part of almost every mobile phone, PDA and laptop. This paper discusses methods for enhancing quality of digital images with focus on removing noise, creating high dynamic range (HDR) images and extending depth of field (DOF). It contains familiarization with technical means for acquiring digital image, explains origin of image noise. Further attention is drawn to HDR, from explaining the term, physical basis, difference between HDR sensing and HDR displaying, to survey and historical development of methods dealing with creating HDR images. The next part is explaining DOF when displaying, physical basis of this phenomenon and review of methods used for DOF extension. The paper mentions problem of acquiring images needed for solving given tasks and designs method for acquiring images. Using it a database of test images for each task was created. Part of the paper also deals with design of a program, that implements discussed methods, for solving the given tasks. With help of proposed class imgmap, quality of output images is improved, by modifying maps of input images. The paper describes methods, improvements, means of setting parameters and their effects on algorithms and control of program using proposed GUI. Finally, comparison with free software for extending DOF takes place. The proposed software provides at least comparable results, the correct setting of parameters for specific cases allows to achieve better properties of the resulting image. Time requirements of image processing are worse because designed software was not optimised.
|
host ::
RSS.