National Repository of Grey Literature 132 records found  1 - 10nextend  jump to record: Search took 0.00 seconds. 
Game Projected on Touch-Enabled Table
Kovaľan, Patrik ; Hradiš, Michal (referee) ; Kapinus, Michal (advisor)
This thesis is about using ARTable for playing card game named Poker. The creation of the thesis is aplication which is transmitted on workspace of the table via projector and controlled with touchscreen. In this system there are components like robotic arm,camera, touchscreen or projector. Robotic arm is used for transporting cards. Camera scans cards and displays then on the touchscreen of the table. Aplication is used to combine digital and real world.
Color-to-Grayscale Video Conversions
Března, Filip ; Hradiš, Michal (referee) ; Čadík, Martin (advisor)
Color to grayscale conversion is still a relevant topic and finds use in multiple areas, to which belongs artistic photography, but primarily colorless print and for simplifying some processes in picture processing. This Bachelor thesis deals with this conversion - decolorization, with focus on video sequences. The basic principle of representation of digital image is explained here alongside with operations for its processing used in next part of thesis. Thereafter it includes the analysis of types of methods, which are used for the conversion to grayscale and further their properties and success rate are evaluated aswell. In the second part of this thesis, there are three chosen and implemented decolorization methods and summary of their achieved results, which is then accompanied by evaluation of practicability in conversion of colorful video sequences to grayscale ones.
Playing Games Using Neural Networks
Buchal, Petr ; Kolář, Martin (referee) ; Hradiš, Michal (advisor)
The aim of this bachelor thesis is to teach a neural network solving classic control theory problems and playing the turn-based game 2048 and several Atari games. It is about the process of the reinforcement learning. I used the Deep Q-learning reinforcement learning algorithm which uses a neural networks. In order to improve a learning efficiency, I enriched the algorithm with several improvements. The enhancements include the addition of a target network, DDQN, dueling neural network architecture and priority experience replay memory. The experiments with classic control theory problems found out that the learning efficiency is most increased by adding a target network. In the game environments, the Deep Q-learning has achieved several times better results than a random player. The results and their analysis can be used for an insight to reinforcement learning algorithms using neural networks and to improve the used techniques.
Deep Learning for Facial Recognition in Video
Jeřábek, Vladimír ; Sochor, Jakub (referee) ; Hradiš, Michal (advisor)
This work deals with face recognition in video using neural networks. In the beginning, there is described the process of selection and verification of convolution neural network to generate feature vectors from images of different identities. In the next part, this work deals with the aggregation of feature vectors from video frames. Aggregation takes place through aggregation neural networks. At the end of this work, the results obtained by the aggregation methods are discussed.
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.
Convolutional Networks for Historic Text Recognition
Macurová, Nela ; Špaňhel, Jakub (referee) ; Hradiš, Michal (advisor)
This thesis deals with the recognition of historical texts using deep neural networks, specifically the recognition of individual words in Gothic script in Czech. Here is a general overview of convolutional networks and text recognition methods. A dataset was created with real and generated data. The network was trained on generated data and testing on real images of words. This proposed word classification method was not very successful due to different test and training data.
Search for Duplicities of Photos
Sklenář, Zdeněk ; Hradiš, Michal (referee) ; Zemčík, Pavel (advisor)
This bachelor thesis is about the analysis, design, implementation and testing of an application which is used to find duplicates in photographs according to its Exif metadata. The application also enables preview of photos, including Exif metadata. Additionally it is possible to filter photos, group duplicities with the original photo, and select the best photos to keep it in accordance with a user-defined parameter, then manually adjust this option, and deleting others. It is also a possible to export selected photos to a ZIP archive.
Deep Learning for Image Classification
Ziková, Jana ; Veľas, Martin (referee) ; Hradiš, Michal (advisor)
This bachelor thesis deals with electronic commerce website products classification using product's photographs. For this purpose we use already implemented models of deep convolutional neural networks. Tho goal of this theses is to design experiments that will lead to the best possible results in product images classification.
Text to Audio Alignment
Šuba, Adam ; Hradiš, Michal (referee) ; Szőke, Igor (advisor)
This bachelor thesis studies a tool for automatic text to audio alignment at the level of single phonemes and graphemes. It also discusses possible techniques used in alignment and possible limitations and difficulties that need to be taken into account. Studied tool uses approach based on grapheme-to-phoneme conversion using joint-sequence models. Data used in experiments are TV broadcast recordings from Multi-Genre Broadcast Challenge 2015.
Restoration of X-Ray Images with Geometric Blur
Sokol, Juraj ; Španěl, Michal (referee) ; Hradiš, Michal (advisor)
This thesis aims to compare various image restoration methods on x-ray images. These methods use point spread function to remove blur introduced in images. These methods are experimentally compared.

National Repository of Grey Literature : 132 records found   1 - 10nextend  jump to record:
Interested in being notified about new results for this query?
Subscribe to the RSS feed.