|
|
Braille Reader
Mezírka, Martin ; Šolony, Marek (referee) ; Maršík, Lukáš (advisor)
This bachelor's thesis concern with problem transforms Braille's documents into text form. At first focus on Braille alphabet and principle of the scanners. Next is represent design of potential method of recognition Braille's documents. At the end is situated description of program's implementation with used library OpenCV and Qt framework. Conclusion discusses reliability and some program's extensions.
|
|
|
Weather Estimation Based on Images of Clouds
Kukaň, Tomáš ; Goldmann, Tomáš (referee) ; Orság, Filip (advisor)
The main purpose of this thesis is a creation of a simple mobile application that would be able to give weather predictions based on a cloud photo through the usage of convolu- tional neural networks. I have analyzed all types of clouds and joined them with weather prediction. Then there are the results of experiments with different neural networks archi- tectures and different datasets. In the end of this thesis I have described the creation of the Android application as well as the problems I had to solve.
|
|
|
Braille Reader
Vicián, Martin ; Polok, Lukáš (referee) ; Maršík, Lukáš (advisor)
The bachelor's paper deals with methods of detection and decoding digitalized documents in braille to Latin script. It describes the function of scanners and their employment in digitalizing braille. It analyzes various methods of thresholding, rotation detection and sign processing. It describes an implemented program in C++ language, the OpenCV library and Qt framework. Finally it proposes the most feasible procedure of decoding.
|
|
|
Mobile Application for Automatic Recording of Chess Games
Jiruška, Adam ; Bobák, Petr (referee) ; Čadík, Martin (advisor)
This thesis is focused on making application for mobile devices, which records progress of chess game. This is achieved by image recognition on input from camera. Chess figures are classified by neural network. Usage of application is during training or real matches to record games and then for analyzing these games. For analyzing, my application offers record in standard algebraic notation. User can also add notes to every game.
|
|
|
Active Learning with Neural Networks
Beneš, Štěpán ; Fajčík, Martin (referee) ; Hradiš, Michal (advisor)
The topic of this thesis is the combination of active learning strategies used in conjunction with deep convolutional networks in image recognition tasks. The goal is to observe the behaviour of selected active learning strategies in a wider array of conditions. The first section of the thesis is dedicated to the theory of active learning, followed by the motivation and challenges of combining them with convolutional neural networks. The goal of this thesis is achieved by a series of experiments, in which the behaviour of active learning strategies is tested for dependencies on the difficulty of the dataset, quality of the learning model, number of training epochs, the size of a batch of samples added in each iteration, the oracle's consistency and the usage of pseudo-labeling technique. The results show the dependency of continuous active learning on the number of training epochs in each iteration and the difficulty of a given dataset. Chosen strategies also seem somewhat resistant to the oracle's faults. The benefits of using pseudo-labeling come hand in hand with the quality of the learning model. Finally, traditional active learning strategies have shown in some cases that they are capable of keeping the pace with modern, tailored strategies.
|
|
|
Automatic Trafic Scene Analysis Using Image Processing
Válek, Lukáš ; Špaňhel, Jakub (referee) ; Zemčík, Pavel (advisor)
Tato práce se zabývá problematikou analýzy scény pomocí metod počítačového vidění. Cílem této práce je vytvořit systém schopný automaticky detekovat anomálie nacházející se ve video záznamech. Práce se zabývá systémy pro detekci a sledování objektů v obraze, tvorbou grafického uživatelského rozhraní a algoritmem pro detekci porušení uživatelem definovaných pravidel. Výsledkem práce je webová aplikace, která uživateli umožňuje správu videozáznamů, definování pravidel pro scénu, zahájení detekce anomálií a zobrazení výsledků analýzy. Systém pracuje v reálném čase, upozorňuje uživatele o dokončení operace a uchovává výsledky analýzy pro další zpracovaní.
|
|
|
Deep learning methods for image processing
Křenek, Jakub ; Chmelík, Jiří (referee) ; Kolář, Radim (advisor)
This master‘s thesis deals with the Deep Learning methods for image recognition tasks from the first methods to the modern ones. The main focus is on convolutional neural nets based models for classification, detection and image segmentation. These methods are used for practical implemetation – counting passing cars on video from traffic camera. After several test of available models, the YOLOv2 architecture was chosen and retrained on own dataset. The application also includes the addition of the SORT tracking algorithm.
|
|
|
Shared Experience in Reinforcement Learning
Mojžíš, Radek ; Šůstek, Martin (referee) ; Hradiš, Michal (advisor)
The aim of this thesis is to use methods of transfer learning for training neural network on a reinforcement learning tasks. As test environment, I am using old 2D console games, such as space invaders or phoenix. I am testing the impact of re-purposing already trained models for different environments. Next I use methods for domain feature transfer. Lastly i focus on the topic of multi-task learning. From the results we can gain insight into possibilities of using transfer learning for reinforcement learning algorithms.
|
|
|
Evaluation of Image Recognition
Kučerová, Pavla ; Mlích, Jozef (referee) ; Zemčík, Pavel (advisor)
This work deals with pattern recognition methods and possibilities of their evaluation. It involves design and implementation of the method comparing the influence of preprocessing to pattern recognition algorithms. The method was tested and evaluated for linear classification algorithm, k-Nearest Neighbors, AdaBoost and SVM.
|
|
| |
guest ::
