|
|
Generation of Synthetic Retinal Images with High Resolution
Aubrecht, Tomáš ; Heidari, Mona (oponent) ; Drahanský, Martin (vedoucí práce)
Special equipment, a fundus camera, is needed to capture the retina, which is the most important part of the human eye. Therefore, the main objective of this work is to design and implement a system that would be able to generate retinal images. The proposed solution uses an image-to-image translation, where the system is provided with a black and white image at the input containing only bloodstream, on the basis of which a color image of the entire retina is generated. The system consists of two neural networks: a generator, which generates retinal images, and a discriminator, which classifies these images as real or synthetic. Training of this system was performed on 141 images from publicly available databases. A new database was created with more than 2,800 images of healthy retinas in a resolution of 1024x1024. This database could be used as a learning tool for ophthalmologists or for the development of various applications working with retinas.
|
|
|
Theoretical and Experimental Determination of the Amount of Information in Human Ocular Biometric Characteristics
Semerád, Lukáš ; Smolík, Luděk (oponent) ; Thorhallsson, Torfi (oponent) ; Drahanský, Martin (vedoucí práce)
The aim of this work is to design method and quantify amount of biometric entropy in the human retina. In other words, this work seeks to determine how unique this biometric feature is, and whether universality is ensured in the human population. The first part shows how the human eye works, especially with regard to the retina. Is also mentioned the physiological basis of angiogenesis in the retina, on which biometric recognition is based in the work's next part. Further are noted ophthalmological devices designed by the STRaDe research group, which are equipped algorithms for detection of the most common diseases in the retina, which are manifested by a visual change. The fourth part presents a tool for generating synthetic retinas, which can be used to create databases for testing other algorithms. Further part deals with the statistical evaluation of the points and properties of the retina, from which it's based the theoretical formula for the calculation retina biometric entropy. In the final chapter are outlined several principles for quantify the mentioned theoretical formula. The work could serve to prove the uniqueness of biometric devices based on retinal scanning, which are currently not very widespread.
|
|
|
Generation of Synthetic Retinal Images with High Resolution
Aubrecht, Tomáš ; Heidari, Mona (oponent) ; Drahanský, Martin (vedoucí práce)
Special equipment, a fundus camera, is needed to capture the retina, which is the most important part of the human eye. Therefore, the main objective of this work is to design and implement a system that would be able to generate retinal images. The proposed solution uses an image-to-image translation, where the system is provided with a black and white image at the input containing only bloodstream, on the basis of which a color image of the entire retina is generated. The system consists of two neural networks: a generator, which generates retinal images, and a discriminator, which classifies these images as real or synthetic. Training of this system was performed on 141 images from publicly available databases. A new database was created with more than 2,800 images of healthy retinas in a resolution of 1024x1024. This database could be used as a learning tool for ophthalmologists or for the development of various applications working with retinas.
|
host ::
RSS.