|
|
Self-supervised learning in computer vision applications
Vančo, Timotej ; Richter, Miloslav (referee) ; Janáková, Ilona (advisor)
The aim of the diploma thesis is to make research of the self-supervised learning in computer vision applications, then to choose a suitable test task with an extensive data set, apply self-supervised methods and evaluate. The theoretical part of the work is focused on the description of methods in computer vision, a detailed description of neural and convolution networks and an extensive explanation and division of self-supervised methods. Conclusion of the theoretical part is devoted to practical applications of the Self-supervised methods in practice. The practical part of the diploma thesis deals with the description of the creation of code for working with datasets and the application of the SSL methods Rotation, SimCLR, MoCo and BYOL in the role of classification and semantic segmentation. Each application of the method is explained in detail and evaluated for various parameters on the large STL10 dataset. Subsequently, the success of the methods is evaluated for different datasets and the limiting conditions in the classification task are named. The practical part concludes with the application of SSL methods for pre-training the encoder in the application of semantic segmentation with the Cityscapes dataset.
|
|
|
Neural Networks for Network Anomaly Detection
Matisko, Maroš ; Martinásek, Zdeněk (referee) ; Blažek, Petr (advisor)
This bachelor thesis is focused on creating a system to mitigate computer network attacks. One of the most common groups of attacks is Distributed Denial of Service (DDoS) attacks, against which this system should protect internal network. In the theoretical part of the thesis are described DDoS attacks, existing systems for their mitigations, neural networks principle and their use. Practical part consists of choosing communication parameters, constructing a neural network with use of these parameters, implementation of this neural network in real–time attack mitigation system and a result of testing of this system.
|
|
|
Quantitative Digital Holographic Microscopy using machine learning
Duša, Martin ; Kolář, Radim (referee) ; Vičar, Tomáš (advisor)
This thesis presents machine learning methods for determining the parameters of micro and nano particles from digital holographic microscopy images. In the theoretical part the principles of hologram imaging, holographic microscopy and the similarity between Mie theory and hologram are presented. The second part of the theoretical review is devoted to machine learning methods used in determining the quantitative information of particles. The practical part is focused on the design of a procedure for determining the position, refractive index and radius using the U-Net architecture implemented in PyTorch and DeepTrack 2.1. The results of the proposed methodologies are discussed at the end of the paper.
|
|
|
Object detection in video using neural networks
Mikulský, Petr ; Sikora, Pavel (referee) ; Myška, Vojtěch (advisor)
This diploma thesis deals with the detection of moving objects in a video recording using neural networks. The aim of the thesis was to detect road users in video recordings. Pre-trained YOLOv5 object detection model was used for a practical part of the thesis. As part of the solution, an own dataset of traffic road video recordings was created and annotated with following classes: a car, a bus, a van, a motorcycle, a truck and a trailer truck. Final version of this dataset comprise 5404 frames and 6467 annotated objects in total. After training, the YOLOv5 model achieved 0.995 mAP, 0.995 precision and 0.986 recall on the dataset. All steps leading to the final form of the dataset are described in the conclusion chapter.
|
|
|
Convolutional Networks for Lip Reading
Kadleček, Josef ; Kišš, Martin (referee) ; Hradiš, Michal (advisor)
This thesis deals with current methods for automatic speech recognition and lip reading via neural networks. Furthermore it deals with similarities in the architectures of neural networks for audio and visual data and available datasets in the field of audiovisual automatic speech recognition. The main contribution of this thesis is set of experiments comparing different changes in neural network architecture and its impact on results. The thesis includes an implementation of a system for automatic speech recognition from audio (CER: 12.6 %) and visual (CER: 57,7 %) data. The architectures of both systems are based on features extraction via convolutional networks followed by recurrent layers LSTM, another layer of convolutions and loss function CTC.
|
|
|
Cell segmentation using convolutional neural networks
Hrdličková, Alžběta ; Chmelík, Jiří (referee) ; Vičar, Tomáš (advisor)
This work examines the use of convolutional neural networks with a focus on semantic and instance segmentation of cells from microscopic images. The theoretical part contains a description of deep neural networks and a summary of widely used convolutional architectures for image segmentation. The practical part of the work is devoted to the creation of a convolutional neural network model based on the U-Net architecture. It also contains cell segmentation of predicted images using three methods, namely thresholding, the watershed and the random walker.
|
|
|
Learning the Face Behind a Voice
Zubalík, Petr ; Mošner, Ladislav (referee) ; Plchot, Oldřich (advisor)
The main goal of this thesis is to design and implement a system that will be able to generate a face based on the speech of a given person. This problem is solved using a system composed of three convolutional neural network models. The first one is based on the ResNet architecture and is used to extract features from speech recordings. The second model is a fully convolutional neural network which converts the extracted features into the styles which form a base for the final facial image. These styles are then passed as an input to the StyleGAN generator, which creates the resulting face. The proposed system is implemented in the Python programming language using the PyTorch framework. The last chapter of the thesis discusses some of the most significant experiments performed to fine-tune and test the developed system.
|
|
|
Image segmentation using machine learning
Matějek, Libor ; Frýza, Tomáš (referee) ; Bravenec, Tomáš (advisor)
This work deals with machine learning and its application in the field of image segmentation and object recognition. The thesis describes the basic terminology related to machine learning and data related to it. It also focuses on the biological nature of the neuron and its technological applications. The basic types of neural networks and the key convolutional neural network for image processing are described. The work also presents the used architectures of convolutional neural networks. Then follow the methods of image preprocessing before the convolutional network R-CNN. Subsequently, some of the datasets suitable for image recognition are analyzed. The implementation is then realized in Python with support for the PyTorch framework from Facebook.
|
|
|
Pedestrian Detection and Recognition in a Multi-Camera System
Macák, Filip ; Orság, Filip (referee) ; Goldmann, Tomáš (advisor)
The main purpose of this bachelor's thesis is to create an application for person detection and recognition from scenes captured in a multi-camera system. The output of the application is a video on which the detected persons are highlighted and each person is assigned an identification number through which it can be recognized across the input scenes. Several solutions to the problem of person detection and recognition were examined and the text of this work serves as an overview of these problems. The application is built on PyTorch and Torchreid libraries. A detector with a Faster-RCNN network is used for detection and recognition is based on the OSNet network. The application also includes a simple user interface to facilitate work with the application. The application serves as a demonstration of the state-of-the-art for person detection and recognition.
|
|
|
Deep learning based QRS delineator
Malina, Ondřej ; Hejč, Jakub (referee) ; Smíšek, Radovan (advisor)
This thesis deals with the issue of automatic measurement of the duration of QRS complexes in ECG signals. Special emphasis is then placed on the possibility of automatic detection of QRS complexes while exciting cardiac tissue with a pacemaker. The content of this work is divided into four logical units, where the first part deals with the heart as an organ. It describes the origin and spread of excitement in the heart, its possible pathologies and their manifestations in ECG recording, it also deals with pacing and measuring ECG recording during simultaneous pacing. The second part of the thesis contains a brief introduction to the topic of machine and deep learning. The third part of the thesis contains a search of current approaches using methods based on deep learning to solve the detection of QRSd. The fourth part deals with the design and implementation of its own model of deep learning, able to detect the beginnings and ends of QRS complexes from ECG recordings. It describes the data preprocessing implemented in the MATLAB programming environment. The actual implementation of the model was performed in the Python using the PyTorch and NumPy moduls.
|
guest ::
