keywords:"image inpainting" - Výsledky hledání - Digitální repozitář

host :: přihlásit Digitální repozitář
		Hledej		Nový záznam		Nápověda		O repozitáři

Hlavní stránka > Výsledky hledání: keywords:"image inpainting"

Hledej:

Tipy pro vyhledávaní :: Rozšířené hledání

Hledej ve sbírkách:

Seřadit podle:	Zobrazit výsledky:	Výstupní formát:

	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. Úplný záznam
	Hardsub Remover Krompaščíková, Emma ; Chlubna, Tomáš (oponent) ; Milet, Tomáš (vedoucí práce) The goal of this thesis is to propose techniques for removing hardcoded subtitles from video and then implement them in the form of a desktop application. The thesis describes and implements four techniques for removing subtitles from an image – two are based on inpainting and other two use image filters to blur the selected area. An optimized method for detecting text in video is described and implemented using bisection, which enables the reduction of the processing time compared to the detection of text on each frame. The library Keras-OCR is used for text detection and the OpenCV library for its removing. Desktop app has a user interface built using the Electron library, image processing is executed using a Python script. Úplný záznam
	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. Úplný záznam

Chcete být upozorněni, pokud se objeví nové záznamy odpovídající tomuto dotazu?
Přihlásit se k odběru RSS.

Digitální repozitář :: :: :: ::
Powered by v1.1.2
Spravuje

Tato stránka je dostupná také v následujících jazycích:
Česky English