|
|
Application for Person Authentication Based on Retinal Images
Moncz, Oliver ; Goldmann, Tomáš (referee) ; Kavetskyi, Andrii (advisor)
This paper deals with the problem of authentication of people based on retinal images. The main objective is to design an algorithm that can match the retinal image with the registered images in the database. The outcome is the determination of identity with a degree of certainty. Another goal was to create an application that allows to perform the mentioned operations through a simple graphical user interface. Lastly, the results are evaluated and compared with existing solutions. The proposed authentication system achieved an average accuracy of 72.46 % for the DRIVE and STARE datasets, and 78.9 % for the FIRE dataset.
|
|
|
Using unlabeled data for retinal segmentation
Shemshur, Andrii ; Jakubíček, Roman (referee) ; Vičar, Tomáš (advisor)
Tato bakalářská práce se zabývá vývojem a hodnocením pokročilých metod pro segmentaci lékařských snímků v kontextu omezených trénovacích dat. Studie zkoumá techniky učení pod dohledem využívající konvoluční neuronové sítě (CNN), přenosové učení s předtrénovanými modely a strategie učení s částečným dohledem. Jako základní model byl použit model konvoluční neuronové sítě (CNN) s dohledem založený na architektuře U-Net, který dosáhl koeficientu Dice 77,6% a průniku nad sjednocením (IoU) 63,4%. Použití přenosového učení pomocí kodéru ResNet34 předtrénovaného na síti ImageNet vedlo k výraznému zlepšení výkonu s koeficientem Dice 81,9%, IoU 69,3% a přesností 96,7%. Kromě toho byly ke zvýšení výkonu modelu použity strategie učení s částečným dohledem, včetně pseudoznačení a předtrénování denoizace. Přístup pseudoznačení přinesl koeficient Dice 81,7% a IoU 69,1%, čímž prokázal účinnost využití neoznačených dat. Přístup před tréninkem denoizace prokázal robustní výkonnost a dosáhl koeficientu Dice 80,3% a IoU 67,0%, a to i v přítomnosti zašuměných a neoznačených dat. Tyto výsledky podtrhují potenciál transferového učení a poloprovozních metod pro zvýšení přesnosti segmentace při analýze lékařských snímků. Poskytují solidní základ pro budoucí výzkum v této oblasti.
|
|
|
Classification of the vascular tree in fundus images
Tebenkova, Iuliia ; Kolář, Radim (referee) ; Odstrčilík, Jan (advisor)
Retinal image analysis plays a very important role, as human gets around 90% of environment information with the help of eyes. Automation of process of retinal image analysis promotes to improve the efficiency of retinal medical examinations. The following thesis is dedicated to automatic classification methods of retinal vascular system images obtained from a digital fundus camera. Vessel classification method using classifier on the base of neural networks, which is trained and then tested on the retinal vessel segments, is investigated and implemented. In this thesis anatomical retinal survey, properties of image data from digital fundus camera and retinal image classification methods are briefly described. The last chapter is devoted to the evaluation of efficiency of retinal vessel classification with automatic methods.
|
|
|
Analysis of Retinal Image Data to Support Glaucoma Diagnosis
Odstrčilík, Jan ; Kybic, Jan (referee) ; Matula,, Petr (referee) ; Kolář, Radim (advisor)
Fundus kamera je široce dostupné zobrazovací zařízení, které umožňuje relativně rychlé a nenákladné vyšetření zadního segmentu oka – sítnice. Z těchto důvodů se mnoho výzkumných pracovišť zaměřuje právě na vývoj automatických metod diagnostiky nemocí sítnice s využitím fundus fotografií. Tato dizertační práce analyzuje současný stav vědeckého poznání v oblasti diagnostiky glaukomu s využitím fundus kamery a navrhuje novou metodiku hodnocení vrstvy nervových vláken (VNV) na sítnici pomocí texturní analýzy. Spolu s touto metodikou je navržena metoda segmentace cévního řečiště sítnice, jakožto další hodnotný příspěvek k současnému stavu řešené problematiky. Segmentace cévního řečiště rovněž slouží jako nezbytný krok předcházející analýzu VNV. Vedle toho práce publikuje novou volně dostupnou databázi snímků sítnice se zlatými standardy pro účely hodnocení automatických metod segmentace cévního řečiště.
|
|
|
Advanced processing of ophthalmologic videosequences of retinal images
Říha, Pavel ; Odstrčilík, Jan (referee) ; Jan, Jiří (advisor)
The diploma thesis deals with registration and analysis of images from the experimental low-cost fundus camera that reaches a low SNR (around 10 dB) and low temporal and spatial resolution. The aim of the diploma tesis is to explore the possibilities of digital processing leading to the creation of a videosequence that has real benefits for medical diagnostics. The well-known program elastix is used for registration. Preprocessing filters and interpolation are implemented in Matlab. The program provides a wide range of setting options, out of which many combinations were tested and evaluated. To assess the accuracy achieved, spatial variations in the detected motion of blood-vessels are evaluated. Best results with a precision below 0.3 px were achieved by using a band-pass filter, a~suitably sized mask, rigid registration and a metric of the mutual information. Test sequences were registered precisely enough both for visual assessment and basic computational analysis. Registered sequences and the developed application that both can be used in the further development of the experimental camera are the main contributions of the diploma thesis.
|
|
|
Analysis of fundus images aimed to localize pathological areas
Hartlová, Marie ; Kolář, Radim (referee) ; Odstrčilík, Jan (advisor)
Diabetic retinopathy is a serious eye complication of diabetes mellitus and one of the major causes of blindness in the world. This thesis deals with detection of neovascularizations, which is the first manifestation of diabetic retinopathy in the retina. In summary, in this thesis describe the properties image data from digital fundus camera, image segmentation methods, methods for automatic blood vessels segmentation and detection of neovaskularizations. This information are used to create own method to detect neovaskularization.
|
|
|
Blood vessel segmentation in fundus images using classification methods
Šťastný, Pavel ; Štohanzlová, Petra (referee) ; Odstrčilík, Jan (advisor)
Segmentation blood vessel the local images of retinal is very important for evaluation and for diagnostics eye’s disease, especially diabetic retinopathy and glaucoma. This bachelor’s thesis is deal with segmentation blood vessel by classification methods. I used simple neural network as a classifier. First of all I taught her by delta rule and then I used matched filtering on the prepare image. At the end I compared all information with gold standard. Average va-lues from score for healthy images were sensitivity 0,7717, specificity 0,9571 and accuracy score 0,9225.
|
|
|
Analysis of Colour Retinal Images Aimed at Segmentation of Vessel Structures
Odstrčilík, Jan ; Jiřík, Radovan (referee) ; Jan, Jiří (advisor)
Segmentation of vessel structure is an important phase in analysis of retinal images. The resulting vessel system description may be important for diagnostic of many eye and cardiovascular diseases. A method for automatic segmentation of the vessel structure in colour retinal images is presented in the thesis. The method utilises 2D matched filtering to detect presence of short linear vessel sections of a particular thickness and orientation. The approach correlates the local image areas with a 2D masks based on a typical brightness profile perpendicular to vessels of a particular width. Three different approximated profiles are used and corresponding matched filters are designed for: thin, medium and thick vessels. The evaluation of typical vessel profiles and filter design are described in chapter 3 and chapter 4. The parametric images obtained by convolution of the image with the masks are then thresholded in order to obtain binary representation of vessel structure. The three binary representations are consequently combined to provide the best available rough vessel map, which is finalised by complementing the obviously missing vessel sections and cleaning the disconnected fractional artefacts. The thresholding algorithm and final steps of processing are mentioned in chapter 5 and chapter 6. The method has been implemented by computer and the program for automatic vessel segmentation has been developed using database of real retinal images. The efficiency of the method has been finally evaluated on images from the standard database DRIVE.
|
|
|
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.
|
|
|
Retinal images in biometry
Bujnošková, Eva ; Drahanský, Martin (referee) ; Kolář, Radim (advisor)
Retinal recognition is very efficient and almost non-fallible tool for persons' identification, thanks its advantages it can be used in cases when high security is needed. Process of the identification comes from successful vessel extraction and the transfer to binary image. After that this is used to look for the vessel bifurcations with help of skeletonization which is one of the operations of mathematical morphology. The parameter of the detection of bifurcations isn't enough therefore there are other information completed - thickness and the direction of vessel in the surroundings of known crossing. The best correlation between the parameters and the images in database is searched, than alignment is made, and with the certain probability the closest image is chosen to be proclaimed as the match. The solution uses also the second method to image processing - the method using image translation and evaluation of minimal distances between found bifurcations.
|
guest ::
