|
|
Detection and evaluation of distorted frames in retinal image data
Vašíčková, Zuzana ; Chmelík, Jiří (referee) ; Kolář, Radim (advisor)
Diplomová práca sa zaoberá detekciou a hodnotením skreslených snímok v retinálnych obrazových dátach. Teoretická časť obsahuje stručné zhrnutie anatómie oka a metód hodnotenia kvality obrazov všeobecne, ako aj konkrétne hodnotenie retinálnych obrazov. Praktická časť bola vypracovaná v programovacom jazyku Python. Obsahuje predspracovanie dostupných retinálnych obrazov za účelom vytvorenia vhodného datasetu. Ďalej je navrhnutá metóda hodnotenia troch typov šumu v skreslených retinálnych obrazoch, presnejšie pomocou Inception-ResNet-v2 modelu. Táto metóda nebola prijateľná a navrhnutá bola teda iná metóda pozostávajúca z dvoch krokov - klasifikácie typu šumu a následného hodnotenia úrovne daného šumu. Pre klasifikáciu typu šumu bolo využité filtrované Fourierove spektrum a na hodnotenie obrazu boli využité príznaky extrahované pomocou ResNet50, ktoré vstupovali do regresného modelu. Táto metóda bola ďalej rozšírená ešte o krok detekcie zašumených snímok v retinálnych sekvenciách.
|
|
|
Quality Check of Text in Forms
Moravec, Zbyněk ; Juránek, Roman (referee) ; Zemčík, Pavel (advisor)
Purpose of this thesis is the quality check of correct button text display on photographed monitors. These photographs contain a variety of image distortions which complicates the following image graphic element recognition. This paper outlines several possibilities to detect buttons on forms and further elaborates on the implemented detection based on contour shapes description. After buttons are found, their defects are detected subsequently. Additionally, this thesis describes an automatic identification of picture with the highest quality for documentation purposes.
|
|
|
Program for evaluating image quality using neural network
Šimíček, Pavel ; Kratochvíl, Tomáš (referee) ; Slanina, Martin (advisor)
This thesis studies the assessment of picture quality using the artificial neural network approach. In the first part, two main ways to evaluate the picture quality are described. It is the subjective assessment of picture quality, where a group of people watches the picture and evaluates its quality, and objective assessment which is based on mathematical relations. Calculation of structural similarity index (SSIM) is analyzed in detail. In the second part, the basis of neural networks is described. A neural network was created in Matlab, designed to simulate subjective assessment scores based on the SSIM index.
|
|
|
Comparison of Image Quality Measuring Methods
Škurla, Adam ; Klíma, Ondřej (referee) ; Bařina, David (advisor)
This thesis is aimed at image quality assessment methods and comparison of their performance regarding compression standards JPEG and JPEG 2000. First part provides information about image quality assessment basics, mentioning existing and used methods. The second part describes approach used to acquire subjective and objective rating of image quality. Further it compares obtained subjective ratings and ratings determined by objective methods. Conclusion provides an evaluation of obtained results and specification of the most suitable methods for measuring quality of images created by compression standards stated above.
|
|
|
Processing of image sequences from fundus camera
Klimeš, Filip ; Odstrčilík, Jan (referee) ; Kolář, Radim (advisor)
Cílem mé diplomové práce bylo navrhnout metodu analýzy retinálních sekvencí, která bude hodnotit kvalitu jednotlivých snímků. V teoretické části se také zabývám vlastnostmi retinálních sekvencí a způsobem registrace snímků z fundus kamery. V praktické části je implementována metoda hodnocení kvality snímků, která je otestována na reálných retinálních sekvencích a vyhodnocena její úspěšnost. Práce hodnotí i vliv této metody na registraci retinálních snímků.
|
|
|
Deep Learning based compression of 360° images
Budáč, Adam ; Boleček, Libor (referee) ; Kufa, Jan (advisor)
This diploma thesis deals with 360° image compression based on deep learning. The thesis describes the representation and deformations of a 360° image. It then describes conventional compression methods and methods using machine learning, deep learning and deep neural networks for 360° image compression. Part of the work is the creation of a dataset, which consists of ten 360° images, and the design of a framework that enables image compression using conventional codecs and algorithms based on machine learning, deep learning, and deep neural networks. Images from the dataset are compressed using five conventional codecs and four deep learning algorithms. The quality of compressed images is measured using seven objective metrics and one subjective test. As a result of the experiment, the conventional methods achieved higher compression quality than the methods using deep learning, and the computational complexity of the conventional methods is lower compared to the methods using deep learning.
|
|
|
Detection and evaluation of distorted frames in retinal image data
Vašíčková, Zuzana ; Chmelík, Jiří (referee) ; Kolář, Radim (advisor)
Diplomová práca sa zaoberá detekciou a hodnotením skreslených snímok v retinálnych obrazových dátach. Teoretická časť obsahuje stručné zhrnutie anatómie oka a metód hodnotenia kvality obrazov všeobecne, ako aj konkrétne hodnotenie retinálnych obrazov. Praktická časť bola vypracovaná v programovacom jazyku Python. Obsahuje predspracovanie dostupných retinálnych obrazov za účelom vytvorenia vhodného datasetu. Ďalej je navrhnutá metóda hodnotenia troch typov šumu v skreslených retinálnych obrazoch, presnejšie pomocou Inception-ResNet-v2 modelu. Táto metóda nebola prijateľná a navrhnutá bola teda iná metóda pozostávajúca z dvoch krokov - klasifikácie typu šumu a následného hodnotenia úrovne daného šumu. Pre klasifikáciu typu šumu bolo využité filtrované Fourierove spektrum a na hodnotenie obrazu boli využité príznaky extrahované pomocou ResNet50, ktoré vstupovali do regresného modelu. Táto metóda bola ďalej rozšírená ešte o krok detekcie zašumených snímok v retinálnych sekvenciách.
|
|
|
Comparison of Image Quality Measuring Methods
Škurla, Adam ; Klíma, Ondřej (referee) ; Bařina, David (advisor)
This thesis is aimed at image quality assessment methods and comparison of their performance regarding compression standards JPEG and JPEG 2000. First part provides information about image quality assessment basics, mentioning existing and used methods. The second part describes approach used to acquire subjective and objective rating of image quality. Further it compares obtained subjective ratings and ratings determined by objective methods. Conclusion provides an evaluation of obtained results and specification of the most suitable methods for measuring quality of images created by compression standards stated above.
|
|
|
Modern Methods for Image Quality Assessment
Nováček, Petr
This paper deals with the comparison of Image Quality Assessment (IQA) algorithms. The test gallery of colour calibre images were captured for comparison of IQA algorithms. Test gallery was captured by two cameras with a different type of sensors – CMOS with Bayer mask and a Foveon sensor.
|
|
|
Quality Check of Text in Forms
Moravec, Zbyněk ; Juránek, Roman (referee) ; Zemčík, Pavel (advisor)
Purpose of this thesis is the quality check of correct button text display on photographed monitors. These photographs contain a variety of image distortions which complicates the following image graphic element recognition. This paper outlines several possibilities to detect buttons on forms and further elaborates on the implemented detection based on contour shapes description. After buttons are found, their defects are detected subsequently. Additionally, this thesis describes an automatic identification of picture with the highest quality for documentation purposes.
|
guest ::
