|
|
Robustní odšumování a dereverberace audia
Košina, Simon ; Skácel, Miroslav (oponent) ; Szőke, Igor (vedoucí práce)
Cieľom tejto práce je vytvorenie modelu pre odšumovanie a dereverberáciu audio nahrávok pochádzajúcich z leteckej VHF komunikácie. Práca popisuje teoretické základy strojového učenia a rôzne architektúry neurónových sieti, ktoré sa v prípade podobných problémov často používajú. Nasleduje popis použitých nástrojov, implementácie a dátových sád. Posledné kapitoly sa venujú vykonaným experimentom, dosiahnutým výsledkom a nadväzujúcej práci.
|
|
|
Reconstruction of Missing Parts of the Face Using Neural Network
Marek, Jan ; Drahanský, Martin (oponent) ; Goldmann, Tomáš (vedoucí práce)
The goal of this thesis is to design a neural network for reconstruction of face images in which a part of the face is obscured by a mask. Concepts used in the development of convolutional neural networks and generative adversarial networks are presented. Specific concepts used in neural networks used for face reconstruction are described. The generative adversarial network presented in this thesis combines the use of gated convolutional layers and dense multiscale fusion blocks to produce realistic reconstructions of masked face images.
|
|
|
Simulation of Skin Diseases Effect Using GAN
Bak, Adam ; Goldmann, Tomáš (oponent) ; Kanich, Ondřej (vedoucí práce)
The aim of this master's thesis is to generate a dataset of synthetic fingerprint images that display symptoms of skin disease. The thesis deals with damage caused by skin disease in the fingerprint images and synthetic fingerprint generation. The diseased fingerprints are generated using a model based on Wasserstein GAN with gradient penalty. A unique diseased fingerprint database created at FIT BUT was used for training of the GAN model. The model was trained on three types of skin disease: atopic eczema, psoriasis vulgaris and dyshidrotic eczema. The generator network of the trained WGAN-GP model was used to generate datasets of synthetic fingerprint images. The synthetic images were compared with real fingerprint images using the NFIQ and FiQiVi quality assessment tools and by comparing minutiae location and minutiae orientation distributions in the fingerprint images.
|
|
|
Generating Faces with Generative Adversarial Networks
Konečný, Daniel ; Herout, Adam (oponent) ; Kolář, Martin (vedoucí práce)
The goal of this thesis is generating color images of faces from randomly chosen high-dimensional vectors with Generative Adversarial Networks. The next task is to analyze input vectors based on the features of faces generated from those vectors. Three different models of Generative Adversarial Network are implemented, one for generating images of handwritten digits and other two for generating images of faces. Generated images show credible-looking faces, but recognizable from real ones with a human eye. Single dimensions of input vectors are analyzed with Student's t-test. Linear Discriminant Analysis is then used to project input vectors into subspaces where the classes of features are separable. Analysis of generated data proves that the input vector can be specifically chosen to generate an image of a face with requested features with probability up to 80 %. The main result of this thesis is a model of Generative Adversarial Network for generating images of faces. A tool for generating images of faces with chosen features is implemented too.
|
|
|
Reconstruction of a Damaged Facial Image
Pleško, Filip ; Orság, Filip (oponent) ; Goldmann, Tomáš (vedoucí práce)
Generative adversarial networks (GANs) are fast evolving technology in image generation field. In this thesis are GANs used for face image reconstruction, where the face was covered with some item. First some necessary theory is explained, and then existing solutions are discussed. In the end, several GAN models are proposed with intention to find out what layers combination work the best for face image reconstruction. The best solutions are combined into final architecture. The final model is also tested on face recognition task to determine whether face reconstruction can be helpful in this task.
|
|
|
Robustní odšumování a dereverberace audia
Košina, Simon ; Skácel, Miroslav (oponent) ; Szőke, Igor (vedoucí práce)
Cieľom tejto práce je vytvorenie modelu pre odšumovanie a dereverberáciu audio nahrávok pochádzajúcich z leteckej VHF komunikácie. Práca popisuje teoretické základy strojového učenia a rôzne architektúry neurónových sieti, ktoré sa v prípade podobných problémov často používajú. Nasleduje popis použitých nástrojov, implementácie a dátových sád. Posledné kapitoly sa venujú vykonaným experimentom, dosiahnutým výsledkom a nadväzujúcej práci.
|
|
|
Simulation of Skin Diseases Effect Using GAN
Bak, Adam ; Goldmann, Tomáš (oponent) ; Kanich, Ondřej (vedoucí práce)
The aim of this master's thesis is to generate a dataset of synthetic fingerprint images that display symptoms of skin disease. The thesis deals with damage caused by skin disease in the fingerprint images and synthetic fingerprint generation. The diseased fingerprints are generated using a model based on Wasserstein GAN with gradient penalty. A unique diseased fingerprint database created at FIT BUT was used for training of the GAN model. The model was trained on three types of skin disease: atopic eczema, psoriasis vulgaris and dyshidrotic eczema. The generator network of the trained WGAN-GP model was used to generate datasets of synthetic fingerprint images. The synthetic images were compared with real fingerprint images using the NFIQ and FiQiVi quality assessment tools and by comparing minutiae location and minutiae orientation distributions in the fingerprint images.
|
|
|
Reconstruction of Missing Parts of the Face Using Neural Network
Marek, Jan ; Drahanský, Martin (oponent) ; Goldmann, Tomáš (vedoucí práce)
The goal of this thesis is to design a neural network for reconstruction of face images in which a part of the face is obscured by a mask. Concepts used in the development of convolutional neural networks and generative adversarial networks are presented. Specific concepts used in neural networks used for face reconstruction are described. The generative adversarial network presented in this thesis combines the use of gated convolutional layers and dense multiscale fusion blocks to produce realistic reconstructions of masked face images.
|
|
|
Generating Faces with Generative Adversarial Networks
Konečný, Daniel ; Herout, Adam (oponent) ; Kolář, Martin (vedoucí práce)
The goal of this thesis is generating color images of faces from randomly chosen high-dimensional vectors with Generative Adversarial Networks. The next task is to analyze input vectors based on the features of faces generated from those vectors. Three different models of Generative Adversarial Network are implemented, one for generating images of handwritten digits and other two for generating images of faces. Generated images show credible-looking faces, but recognizable from real ones with a human eye. Single dimensions of input vectors are analyzed with Student's t-test. Linear Discriminant Analysis is then used to project input vectors into subspaces where the classes of features are separable. Analysis of generated data proves that the input vector can be specifically chosen to generate an image of a face with requested features with probability up to 80 %. The main result of this thesis is a model of Generative Adversarial Network for generating images of faces. A tool for generating images of faces with chosen features is implemented too.
|
|
|
Generování realistických snímků obloh
Špaček, Jan ; Wilkie, Alexander (vedoucí práce) ; Pilát, Martin (oponent)
Generování realistických snímků obloh Naším cílem je generovat realistické obrázky oblohy s oblačností pomocí generativních kompetitivních sítí (GAN). Zkoumáme dvě architektury GANů, ProGAN a StyleGAN, a zjišťujeme, že StyleGAN dosahuje významně lepších výsledků. Pro generování obrázků ve velmi vysokém rozlišení, které nemůže být efektivně zpracováno soudobými architekturami GANů, navrhujeme novou architekturu SuperGAN. 1
|
host ::
RSS.