|
|
Biometry based on retinal videosequences
Oweis, Kamil ; Odstrčilík, Jan (referee) ; Kolář, Radim (advisor)
The biometric methods are the most advanced methods for recognition and verification of person identity. These methods are quite fast, safe and applicable in different situations. In this thesis is used a set of retinal scans taken with a video-ophtalmoscope. These pictures are further modified for next processing, first of all by convertion into black-andwhite binary image, in some cases was after that used a binary matrix for description of image. Afterwards was suggested comparison method of images from the database with reference image of the retina: method of overlap and shift. It was tested a set of blackand-white and then also grey images. All method calculations was realized in program Matlab of which outcome was determination of the most congruent image with reference image and evaluation of overall program accuracy.
|
|
| |
|
| |
|
|
Identification of persons using retinal biometry
Klimešová, Lenka ; Mézl, Martin (referee) ; Odstrčilík, Jan (advisor)
This paper deals with identification of persons using retinal biometry. The retinal vasculature is invariant and unique to everyone, which determines it for biometric purposes. The first part of the work includes information about biometrics, biometric systems and reliability measures. The next part describes the principle of using experimental video ophthalmoscope, which was used for retinal vascular imaging and includes the literature research of use of retinal images for biometrics, feature extraction methods and similarity measures. Finally, two algorithms to use the input data are proposed and realized in programming environment MATLAB®. The methods are tested and evaluated on a data set from experimental video ophthalmoscope and on publicly available STRaDe and DRIVE databases.
|
|
|
Analysis of temporal retinal sequences
Nováková, Marie ; Odstrčilík, Jan (referee) ; Kolář, Radim (advisor)
This thesis deals with a method of the retinal image acquisition by fundus camera, their properties and evaluation of the retinal vessel diameter from acquired images. Several studies dealing with usage of retinal vessels diameters for hypertension, cardiovascular diseases, diabetes mellitus and glaucoma are described. The second part of this thesis is focused on the extraction of the retinal blood-vessels pulsation from retinal sequences and the basic processing of extracted pulsation signals. The proposed method is described in details and tested on one dataset.
|
|
|
Blood vessel segmentation in fundus images using mathematical morphology
Stonawski, Stanislav ; Jan, Jiří (referee) ; Odstrčilík, Jan (advisor)
Segmentation of retinal blood vessel is an important step in the fundus image analysis. The resulting image can be used to diagnose ophthalmic or cardiovascular diseases. The aim of this thesis is to search for possibilities of high resolution eye fundus image processing while using mathematical morphology methods. This should lead to the creation of an algorithm capable of blood vessel segmentation. The thesis provides information on fundus camera, image, blood vessel properties and mathematical morphology filtering methods. The created algorithms and the proposed method based on them are presented, including their performance analysis based on the HRF database processing.
|
|
|
Implementation of Algorithm for Recognition of Eye Retina
Ondroušek, Jan ; Stružka, Jaroslav (referee) ; Hájek, Josef (advisor)
Vessel structure is a very important element in medical sience for diagnosis of eye and cardiovascular diseases. Therefore, its automatic segmentation is very important too. In introduction there is a short description of eye retina. After that, method of implementation is presented according to Ing. Jan Odstrčilík's thesis - Analyze of colour retinal images aimed to segmentation of vessel structures created under the auspices of Brno University of Technology - Faculty of Electrical Engineering and Communication, Department of Biomedical Engineering in 2008. This method is based on filtering input image with properly designed filtering masks, followed by thresholding with properly calculated value and finally cleaning result image from artefacts. Algorithm was written in C++ language. All important functions were implemented for purpose of given method with consideration on speed and accuray. Main sections of source code with description of user interface are introduced next in this thesis. At the end, the implementation was tested on real images from ÚBMI and DRIVE databases, results were recorded, expansions and adjustments possibilities of implementation were debated.
|
|
|
Arteries and veins segmentation in retinal images
Šumberová, Dagmara ; Odstrčilík, Jan (referee) ; Kolář, Radim (advisor)
This thesis deals with the necessity of vascular segmentation in digital image analysis of the retina and thein subsequent classification.It briefly describes the segmentation of vessels using matched filtering. Next part of this thesis is focused on processing of the retinal images, their manual segmentation and subsequent testing to determine the best discriminating parameters for classification. Finally there is an evaluation of measured parameters and the propřed extension of this method.
|
|
|
Identification of persons using retinal biometry
Klimešová, Lenka ; Mézl, Martin (referee) ; Odstrčilík, Jan (advisor)
This paper deals with identification of persons using retinal biometry. The retinal vasculature is invariant and unique to everyone, which determines it for biometric purposes. The first part of the work includes information about biometrics, biometric systems and reliability measures. The next part describes the principle of using experimental video ophthalmoscope, which was used for retinal vascular imaging and includes the literature research of use of retinal images for biometrics, feature extraction methods and similarity measures. Finally, two algorithms to use the input data are proposed and realized in programming environment MATLAB®. The methods are tested and evaluated on a data set from experimental video ophthalmoscope and on publicly available STRaDe and DRIVE databases.
|
|
|
Biometry based on retinal videosequences
Oweis, Kamil ; Odstrčilík, Jan (referee) ; Kolář, Radim (advisor)
The biometric methods are the most advanced methods for recognition and verification of person identity. These methods are quite fast, safe and applicable in different situations. In this thesis is used a set of retinal scans taken with a video-ophtalmoscope. These pictures are further modified for next processing, first of all by convertion into black-andwhite binary image, in some cases was after that used a binary matrix for description of image. Afterwards was suggested comparison method of images from the database with reference image of the retina: method of overlap and shift. It was tested a set of blackand-white and then also grey images. All method calculations was realized in program Matlab of which outcome was determination of the most congruent image with reference image and evaluation of overall program accuracy.
|
guest ::
