|
|
Segmentation of arterial wall in high resolution retinal images
Polachová, Natálie ; Odstrčilík, Jan (referee) ; Kolář, Radim (advisor)
This thesis focuses on automatic segmentation of retinal arterial walls in images acquired using adaptive optics. Adaptive optics is a non-invasive imaging method that provides high lateral resolution and allows detailed observation of retinal microstructures, including arterial walls. This technology is crucial for early diagnosis of serious diseases such as arterial hypertension and diabetic retinopathy. The main objective of this work was to detect the arterial lumen and segment its walls. Morphological and filtration techniques were used for lumen detection. For arterial wall segmentation, brightness profiles along the detected lumen were analyzed and active contour and spline methods were used. The results show that the active contour segmentation method improves the accuracy of arterial wall detection, especially in high-contrast regions. This thesis summarizes the findings and proposes improvements in the detection of the inner side of the arterial wall, which reduces the segmentation success rate in this work.
|
|
|
Segmentation of important structures in retinal images
Trojánek, Václav ; Mézl, Martin (referee) ; Odstrčilík, Jan (advisor)
This bachelor thesis focuses on the segmentation of significant structures in retinal image data to improve the diagnosis and treatment of ocular diseases. Methods of retinal image analysis are investigated and implemented in this thesis. The thesis begins with an overview of the anatomy of the eye and the principles of background eye imaging using a fundus camera and an experimental video ophthalmoscope. This is followed by a detailed literature search focusing on current methods for the detection and segmentation of diagnostically important structures such as the optic disc, macula and blood vessels. A key part of the work is the implementation and testing of selected algorithms, including Hough transform for optic disc detection and OTSU thresholding for blood vessel segmentation and yellow spot detection based on previous optic disc segmentation.
|
|
|
Conversion of fingerprints captured by a mobile device into a standardized format - image editing
Mucha, Vojtěch ; Říha, Kamil (referee) ; Číka, Petr (advisor)
This bachelor thesis deals with the issue of fingerprint conversion taken by a mobile device into a standardized format. In the present day, mobile devices are used more and more often to acquire biometric data, fingerprints included. Processing and standardization of such data is an essential part of the subsequent biometric analysis. The aim of the work is to design and implement an algorithm which would convert a photo of a finger into a grey scale picture of its fingerprint with distinct papillary lines and subdued valleys. The algorithm is implemented in C++ using OpenCV library and a trained neural network for finger detection from hand image. The achieved results are evaluated according to the algorithms for assessing the quality of fingerprints NFIQ 2 and Innovatrics.
|
|
|
Market segmentation using statistical methods
Bystřická, Michaela ; Marciánová, Pavla (referee) ; Schüller, David (advisor)
The thesis is focused on the segmentation of customers of selected summer swimming pool. The first part of the thesis is devoted to the theoretical concept of the chosen issue. In the analytical part, a summer swimming pool is presented and selected analyses are carried out. The analytical part also includes a questionnaire survey. In the last part of the thesis, measures are proposed that would lead to an increase in the level of services for the selected customer segment.
|
|
| |
|
|
Road and path segmentation in images for autonomous driving scenario
Janíček, Ondřej ; Cihlář, Miloš (referee) ; Svědiroh, Stanislav (advisor)
This bachelor's thesis deals with the topic of segmentation of roads and paths for the purposes of autonomous driving. In the theoretical part, it deals with computer vision, simple segmentation methods, and practical solutions to the problem using convolutional neural networks and classical methods. In the practical part, the work deals with the collection of test data, the selection of a suitable programming language, and the selection of suitable libraries. Subsequently, the procedure for programming our own solution will be presented. Here it starts with pre-processing to convert the image into a grayscale image and filtering the noise, then finding the edges in the image using the Canny edge detector, followed by the definition of the region of interest, with the subsequent Hough transform to detect the straight lines in the image, and in the last stage, filtering the horizontal lines and averaging the remaining lines. At the end of the thesis, the results of the presented solution are compared with respect to robustness and computational complexity.
|
|
| |
|
|
Segmentation of Electrocardiographic Signals Using Deep Learning Methods
Hejč, Jakub ; Černý, Martin (referee) ; Halámek, Josef (referee) ; Kolářová, Jana (advisor)
The thesis deals with deep learning methods for the segmentation of surface and intracardiac electrocardiographic recording with focus on atrial activity. The theoretical part introduces current segmentation aproaches of electrocardiographic signals. Issues related to the development of deep learning models in context of standard ECG databases were also discussed. We proposed a pipeling for processing multimodal electrophysiology data from interventional procedures in order to build reliable training datasets. A deep model for segmentation of intracardiac recordings based on a modified residual architecture was proposed. A series of experiments was conducted to evaluate the effect of both model and dataset properties on segmentation quality. The annotation methodology of recordings with atrial fibrillation proved to be a crucial factor. Properties of loss function and type of data augmentation were revealed as secondary important parameters. A novel P wave segmentation method for incomplete references was proposed in the thesis. The approach was inspired by the deep contrast learning. It was modified to distinguish local segments of signals at different levels of abstraction of the extracted feature maps. Results were analyzed using standard quality metrics and post-hoc visual analysis. In some cases, a statistical comparison of experiments for different settings was performed. The results of the work showed that it is possible to use intracardiac signals for embedding a vector representation of local atrial activation into deep models.
|
|
|
Ischemic thrombus analysis in multiphasic brain stroke CT data
Mikešová, Tereza ; Holeček, Tomáš (referee) ; Jakubíček, Roman (advisor)
This master thesis deals with analysis of ischemic thrombus in brain CT scans. In theoretical part, a review of methods, especially thrombus segmentation, is developed. Furthermore, the anatomy of cerebral arteries and acute ischemic stroke is summarized. Selected methods from the field of image processing are briefly described. The practical part results in a comparison of thrombus segmentation methods. The segmentation itself was preceded by data preprocessing, which is described in the theses, and the creation of a manual annotation database. The best implemented method was found to be the adaptive thresholding method, which achieved a Dice score of 0,4555. By combining the methods appropriately, a final Dice score of 0,5145 was achieved. Thrombus parameters were then calculated from the segmented volumes. The median intensity value was 51,55~HU, the median length was 15,16 mm, and the median volume was determined to be 65,34 mm3. Subsequent correlation analysis showed no significant relationship between the derived parameters.
|
|
|
Deep Learning in Historical Geography
Vynikal, Jakub ; Pacina, Jan
In relation to the rapid development of artificial intelligence, the possibilities of automatic processing of spatial data are increasing. Scanned topographical maps are a valued source of historical information. Neural networks allow us to extract information quickly and efficiently from such data, eliminating the difficult and repetitive work that would otherwise have to be done by a human. The article presents two case studies exploring the possibilities of using deep learning in historical geography. The first one is concerned with detecting and extracting swamps from topographic maps, while the second one attempts to automatically vectorize contours from the State Map 1 : 5 000
|
guest ::
