| |
| |
|
Detection and evaluation of distorted frames in retinal image data
Vašíčková, Zuzana ; Chmelík, Jiří (oponent) ; Kolář, Radim (vedoucí práce)
The master's thesis deals with detection and evaluation of distorted frames in retinal image data. The theoretical part contains brief summary of eye anatomy and methods for image quality assessment generally, and also particularly on retinal images. The practical part is carried out in programming language Python. It contains preprocessing of the available retinal images in order to create an appropriate dataset. Further a method for evaluation of three types of blur in distorted retinal images is proposed, specifically Inception-ResNet-v2 model. This method is not feasible and thus another method consisting of two steps is designed - classification of the type of blur and subsequently evaluation of the particular blur level. Filtered Fourier spectrum is used to classify the type of blur and features extracted by ResNet50 serve as the input for regression model. This method is further extended with initial step of detection of blurred frames in retinal sequences.
|
|
Sleep scoring using artificial neural networks
Vašíčková, Zuzana ; Mézl, Martin (oponent) ; Králík, Martin (vedoucí práce)
The main objective of the thesis is to create an artificial neural network for sleep-staging. Firstly, information about sleep and sleep stages is summarized. However, more profound overview of signal processing methods and methods of classification is found in next chapters. After summarizing the theoretical knowledge necessary to carry out practical part of thesis, signal features were extracted according to the theoretical proposal and using statistical analysis, convenient features were used as in input for artificial neural network, able to classify the sleep data into sleep stages after the learning stage.
|
|
Detection and evaluation of distorted frames in retinal image data
Vašíčková, Zuzana ; Chmelík, Jiří (oponent) ; Kolář, Radim (vedoucí práce)
The master's thesis deals with detection and evaluation of distorted frames in retinal image data. The theoretical part contains brief summary of eye anatomy and methods for image quality assessment generally, and also particularly on retinal images. The practical part is carried out in programming language Python. It contains preprocessing of the available retinal images in order to create an appropriate dataset. Further a method for evaluation of three types of blur in distorted retinal images is proposed, specifically Inception-ResNet-v2 model. This method is not feasible and thus another method consisting of two steps is designed - classification of the type of blur and subsequently evaluation of the particular blur level. Filtered Fourier spectrum is used to classify the type of blur and features extracted by ResNet50 serve as the input for regression model. This method is further extended with initial step of detection of blurred frames in retinal sequences.
|
|
Sleep scoring using artificial neural networks
Vašíčková, Zuzana ; Mézl, Martin (oponent) ; Králík, Martin (vedoucí práce)
The main objective of the thesis is to create an artificial neural network for sleep-staging. Firstly, information about sleep and sleep stages is summarized. However, more profound overview of signal processing methods and methods of classification is found in next chapters. After summarizing the theoretical knowledge necessary to carry out practical part of thesis, signal features were extracted according to the theoretical proposal and using statistical analysis, convenient features were used as in input for artificial neural network, able to classify the sleep data into sleep stages after the learning stage.
|
|
Vývoj fantastiky jako literárního žánru, dnešní fantasy trend a jeho vliv na knihovny a knižní trh v České republice
Vašíčková, Zuzana ; Buřilová, Marcela (vedoucí práce) ; Hubrtová, Jitka (oponent)
Práce se zaměřuje na historický vývoj fantastické literatury jako literárního žánru, od počátku novověku do současnosti. Tento vývoj je sledován v zahraničí i v České republice. Kromě vývoje zde můžeme nalézt i definice jednotlivých žánrů. Dále práce sleduje, jak se se současným trendem obliby fantastické literatury potýkají veřejné knihovny. Zmíněny jsou zde problémy spojené s popisem dokumentů, stavba fondu, akvizice, ale i výhody plynoucí z obliby žánru - kdy knihovny fantastiku využívají ke své propagaci. V závěru práce v krátkosti mapuje současný stav knižního trhu a jeho podíl, který zabírá fantastická literatura. V přílohách je pak možné najít orientační výčet subžánrů fantastiky.
|