|
|
Mushroom Detection and Recognition in Natural Environment
Steinhauser, Dominik ; Juránek, Roman (referee) ; Špaňhel, Jakub (advisor)
In this thesis is handled the problem of mushroom detection and recognition in natural environment. Convolutional neural networks are used. The beginning of this thesis is dedicated to the theory of neural networks. Further is solved the problem of object detection and classification. Using neural network trained for classification is solved also the task of localization. Results of trained CNNs are analised.
|
|
|
Neural networks for automatic speaker, language, and sex identification
Do, Ngoc ; Jurčíček, Filip (advisor) ; Peterek, Nino (referee)
Title: Neural networks for automatic speaker, language, and sex identifica- tion Author: Bich-Ngoc Do Department: Institute of Formal and Applied Linguistics Supervisor: Ing. Mgr. Filip Jurek, Ph.D., Institute of Formal and Applied Linguistics and Dr. Marco Wiering, Faculty of Mathematics and Natural Sciences, University of Groningen Abstract: Speaker recognition is a challenging task and has applications in many areas, such as access control or forensic science. On the other hand, in recent years, deep learning paradigm and its branch, deep neural networks have emerged as powerful machine learning techniques and achieved state-of- the-art in many fields of natural language processing and speech technology. Therefore, the aim of this work is to explore the capability of a deep neural network model, recurrent neural networks, in speaker recognition. Our pro- posed systems are evaluated on TIMIT corpus using speaker identification task. In comparison with other systems in the same test conditions, our systems could not surpass reference ones due to the sparsity of validation data. In general, our experiments show that the best system configuration is a combination of MFCCs with their dynamic features and a recurrent neural network model. We also experiment recurrent neural networks and convo- lutional neural...
|
|
|
Multitasking as a result of audiovisual media convergence
Mičke, David ; Moravec, Václav (advisor) ; Kasík, Pavel (referee)
The primary objective of this work is to determine the extent of media multitasking, as an increasing phenomenon in receptioning media content in the last 20 years; on news channels broadcast. The research sample consists of Czech station CT24, BBC and international version of the American CNN. In the theoretical section, the media convergence is explained in the basic terms and concepts; Following to this section, the thesis includes also a part dedicated to particular consequences of convergence in audiovisual media, which is associated with the multitasking. Moreover, the thesis also reflects multitasking's origin, reasons of its development and its impacts on human cognitive perception. On account of multitasking as a developing form of media reception, news channels react. In image analysis of technical codes associated with multitasking, which was undertaken at all channels for one week, are highlighted multitasking specifics of those channels. Included is a comparison of the differences between those news channels.
|
|
|
Media image of the crimean crisis on Russia Today, CNN and ČT24 news
Štěpán, Petr ; Lokšík, Martin (advisor) ; Nečas, Vlastimil (referee)
This thesis analyses how three television stations - Czech ČT24, Russian RT and American CNN - informed about the Crimean crisis which took place in Ukraine in 2014. The first part of the thesis presents theoretical approach and mentions previous similar studies, which focused on examining of medial coverage and framing of war conflicts. Next chapter describes the history of Ukraine briefly and underlines events which could have caused the Crimean crisis. Thereafter the thesis introduces the timeline of the Crimean crisis. In the next part the thesis analyses sources, topics and keywords which appeared in the news of ČT24, RT and CNN. It also describes how particular people and events were visually covered. In the final chapter the approach of the three examined television channels is compared.
|
|
|
Image segmentation using deeplearning methods
Lukačovič, Martin ; Burget, Radim (referee) ; Mašek, Jan (advisor)
This thesis deals with the current methods of semantic segmentation using deep learning. Other approaches of neaural networks in the area of deep learning are also discussed. It contains historical solutions of neural networks, their development, and basic principle. Convolutional neural networks are nowadays the most preferable networks in solving tasks as detection, classification, and image segmentation. The functionality was verified on a freely available environment based on conditional random fields as recurrent neural networks and compered with the deep convolutional neural networks using conditional random fields as postprocess. The latter mentioned method has become the basis for training of new models on two different datasets. There are various enviroments used to implement neural networks using deep learning, which offer diverse perform possibilities. For demonstration purposes a Python application leveraging the BVLC\,/\,Caffe framework was created. The best achieved accuracy of a trained model for clothing segmentation is 50,74\,\% and 68,52\,\% for segmentation of VOC objects. The application aims to allow interaction with image segmentation based on trained models.
|
|
| |
|
|
Image Captioning with Recurrent Neural Networks
Kvita, Jakub ; Španěl, Michal (referee) ; Hradiš, Michal (advisor)
Tato práce se zabývá automatickým generovaním popisů obrázků s využitím několika druhů neuronových sítí. Práce je založena na článcích z MS COCO Captioning Challenge 2015 a znakových jazykových modelech, popularizovaných A. Karpathym. Navržený model je kombinací konvoluční a rekurentní neuronové sítě s architekturou kodér--dekodér. Vektor reprezentující zakódovaný obrázek je předáván jazykovému modelu jako hodnoty paměti LSTM vrstev v síti. Práce zkoumá, na jaké úrovni je model s takto jednoduchou architekturou schopen popisovat obrázky a jak si stojí v porovnání s ostatními současnými modely. Jedním ze závěrů práce je, že navržená architektura není dostatečná pro jakýkoli popis obrázků.
|
guest ::
