Redukcia tieňov v obraze
| dc.contributor.advisor | Fabián, Tomáš | |
| dc.contributor.author | Koniar, Marcel | |
| dc.contributor.referee | Holuša, Michael | |
| dc.date.accepted | 2020-06-24 | |
| dc.date.accessioned | 2020-10-02T09:27:31Z | |
| dc.date.available | 2020-10-02T09:27:31Z | |
| dc.date.issued | 2020 | |
| dc.description.abstract | V diplomovej práci sa zaoberám problematikou redukcie tieňov v obraze. Cieľom práce je vytvorenie aplikácie pre detekciu a redukciu tieňov s využitím konvolučných neurónových sietí. Pre tvorbu aplikácie som zvolil programovací jazyk Python a framework pre strojové učenie TensorFlow. V úvodnej časti práce popisujem techniky pre redukciu tieňov bez strojového učenia a so strojovým učením. Práca ďalej obsahuje popis sietí pre generovanie obrázkov Generative Adversarial Networks (GAN). Následne sa v ďalšej kapitole venujem detailnému postupu praktickej časti, ktorá zahŕňa implementáciu zvolenej siete Stacked Conditional Generative Adversarial Network (ST-CGAN). V závere vyhodnocujem dosiahnuté výsledky a osobný prínos práce. | cs |
| dc.description.abstract | The diploma thesis adresses the issues of reducing shadows in an image. The aim of the thesis is to create an application for the detection and reduction of shadows using convolution neural networks. For the creation of the application, I chose the programming language Python and the framework for the machine learning TensorFlow. In the introductory part of the thesis, I describe techniques to reduce shadows, both without and with machine learning. The study further includes a description of networks for generating images of Generative Adversarial Networks (GAN). Subsequently, in the next chapter I am concerned with a detailed procedure of the practical part, which includes an implementation of the selected network Stacked Conditional Generative Adversarial Network (ST-CGAN). In conclusion, I evaluate the achievements and personal benefits of the study. | en |
| dc.description.department | 460 - Katedra informatiky | cs |
| dc.description.result | výborně | cs |
| dc.format.extent | 19458166 bytes | |
| dc.format.mimetype | application/pdf | |
| dc.identifier.other | OSD002 | |
| dc.identifier.sender | S2724 | |
| dc.identifier.thesis | KON0293_FEI_N2647_2612T025_2020 | |
| dc.identifier.uri | http://hdl.handle.net/10084/142023 | |
| dc.language.iso | sk | |
| dc.publisher | Vysoká škola báňská – Technická univerzita Ostrava | cs |
| dc.rights.access | openAccess | |
| dc.subject | Python | cs |
| dc.subject | Tensorflow | cs |
| dc.subject | GAN | cs |
| dc.subject | ST-CGAN | cs |
| dc.subject | redukcia tieňov | cs |
| dc.subject | analýza obrazu | cs |
| dc.subject | hlboké neurónové siete | cs |
| dc.subject | Python | en |
| dc.subject | Tensorflow | en |
| dc.subject | GAN | en |
| dc.subject | ST-CGAN | en |
| dc.subject | shadow removal | en |
| dc.subject | image analysis | en |
| dc.subject | deep neural networks | en |
| dc.thesis.degree-branch | Informatika a výpočetní technika | cs |
| dc.thesis.degree-grantor | Vysoká škola báňská – Technická univerzita Ostrava. Fakulta elektrotechniky a informatiky | cs |
| dc.thesis.degree-level | Magisterský studijní program | cs |
| dc.thesis.degree-name | Ing. | |
| dc.thesis.degree-program | Informační a komunikační technologie | cs |
| dc.title | Redukcia tieňov v obraze | sk |
| dc.title.alternative | Redukce stínů v obrazech | cs |
| dc.title.alternative | Shadow Removal in Images | en |
| dc.type | Diplomová práce | cs |
Files
Original bundle
1 - 4 out of 4 results
Loading...
- Name:
- KON0293_FEI_N2647_2612T025_2020.pdf
- Size:
- 18.56 MB
- Format:
- Adobe Portable Document Format
- Description:
- Text práce
Loading...
- Name:
- KON0293_FEI_N2647_2612T025_2020_priloha.zip
- Size:
- 9.39 KB
- Format:
- Unknown data format
- Description:
- Příloha
Loading...
- Name:
- KON0293_FEI_N2647_2612T025_2020_posudek_vedouci_Fabian_Tomas.pdf
- Size:
- 56.15 KB
- Format:
- Adobe Portable Document Format
- Description:
- Posudek vedoucího – Fabián, Tomáš
Loading...
- Name:
- KON0293_FEI_N2647_2612T025_2020_posudek_oponent_Holusa_Michael.pdf
- Size:
- 56.83 KB
- Format:
- Adobe Portable Document Format
- Description:
- Posudek oponenta – Holuša, Michael