|
|
Advanced retinal vessel segmentation methods in colour fundus images
Svoboda, Ondřej ; Jan, Jiří (referee) ; Odstrčilík, Jan (advisor)
Segmentation of vasculature tree is an important step of the process of image processing. There are many methods of automatic blood vessel segmentation. These methods are based on matched filters, pattern recognition or image classification. Use of automatic retinal image processing greatly simplifies and accelerates retinal images diagnosis. The aim of the automatic image segmentation algorithms is thresholding. This work primarily deals with retinal image thresholding. We discuss a few works using local and global image thresholding and supervised image classification to segmentation of blood tree from retinal images. Subsequently is to set of results from two different methods used image classification and discuss effectiveness of the vessel segmentation. Use image classification instead of global thresholding changed statistics of first method on healthy part of HRF. Sensitivity and accuracy decreased to 62,32 %, respectively 94,99 %. Specificity increased to 95,75 %. Second method achieved sensitivity 69.24 %, specificity 98.86% and 95.29 % accuracy. Combining the results of both methods achieved sensitivity up to72.48%, specificity to 98.59% and the accuracy to 95.75%. This confirmed the assumption that the classifier will achieve better results. At the same time, was shown that extend the feature vector combining the results from both methods have increased sensitivity, specificity and accuracy.
|
|
|
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.
|
|
|
Retinal image registration based on binary vessel tree
Klímová, Jana ; Kolář, Radim (referee) ; Harabiš, Vratislav (advisor)
This bachelor’s thesis treats of binary retinal image registration. The images were photographed with a fundus camera and consequently a vessel tree has been segmented. Two binary images of the same retina have been acquired. The aim of this thesis is to acquaint with and describe methods of retinal image segmentation and registration and to suggest a process of binary image registration. The image registration is based on binary vessel tree, which is segmented with an already existing computer programme. One of the images is referred to as the reference or source and the second image is referred to as the transformed or sensed. Two image registration methods have been proposed. The first one is based on 2D transformation and image subtraction. The sensed image is rotated and translated to the position where the vessel tree is overlaid and the images are geometrically aligned. The second method uses detection of blood vessel bifurcation in the binary retinal images.
|
|
|
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.
|
|
|
Retinal image registration based on binary vessel tree
Klímová, Jana ; Kolář, Radim (referee) ; Harabiš, Vratislav (advisor)
This bachelor’s thesis treats of binary retinal image registration. The images were photographed with a fundus camera and consequently a vessel tree has been segmented. Two binary images of the same retina have been acquired. The aim of this thesis is to acquaint with and describe methods of retinal image segmentation and registration and to suggest a process of binary image registration. The image registration is based on binary vessel tree, which is segmented with an already existing computer programme. One of the images is referred to as the reference or source and the second image is referred to as the transformed or sensed. Two image registration methods have been proposed. The first one is based on 2D transformation and image subtraction. The sensed image is rotated and translated to the position where the vessel tree is overlaid and the images are geometrically aligned. The second method uses detection of blood vessel bifurcation in the binary retinal images.
|
|
|
Advanced retinal vessel segmentation methods in colour fundus images
Svoboda, Ondřej ; Jan, Jiří (referee) ; Odstrčilík, Jan (advisor)
Segmentation of vasculature tree is an important step of the process of image processing. There are many methods of automatic blood vessel segmentation. These methods are based on matched filters, pattern recognition or image classification. Use of automatic retinal image processing greatly simplifies and accelerates retinal images diagnosis. The aim of the automatic image segmentation algorithms is thresholding. This work primarily deals with retinal image thresholding. We discuss a few works using local and global image thresholding and supervised image classification to segmentation of blood tree from retinal images. Subsequently is to set of results from two different methods used image classification and discuss effectiveness of the vessel segmentation. Use image classification instead of global thresholding changed statistics of first method on healthy part of HRF. Sensitivity and accuracy decreased to 62,32 %, respectively 94,99 %. Specificity increased to 95,75 %. Second method achieved sensitivity 69.24 %, specificity 98.86% and 95.29 % accuracy. Combining the results of both methods achieved sensitivity up to72.48%, specificity to 98.59% and the accuracy to 95.75%. This confirmed the assumption that the classifier will achieve better results. At the same time, was shown that extend the feature vector combining the results from both methods have increased sensitivity, specificity and accuracy.
|
guest ::
