|
|
Extraction of texture features aimed to detect glaucoma defects
Daněk, Daniel ; Kolář, Radim (referee) ; Odstrčilík, Jan (advisor)
The thesis deals with an automatic method of texture analysis using Markov random fields texture modeling. The main aim of this work is to find out relevant textural features, which can be used for appropriate classification of the degree of retinal nerve fiber layer loss. The model of Markovian statistic uses a circular symmetric neighborhood structure and a least square error estimation of the model's parameter. Obtained textural features were quantitatively evaluated using correlation analysis. The results show, that there is a significant correlation between proposed textural features and RNFL thickness measured by OCT. Thus, the features can potentially serve for glaucoma diagnosis.
|
|
|
Automatic Segmentation of Documents Stored as Images
Jakub, Dušan ; Španěl, Michal (referee) ; Szőke, Igor (advisor)
This work deals with dividing the documents stored as images into three groups of segments - background, text and graphics. It introduces various solutions and the method using Gabor filters and artficial neural networks is described in detail. The selection of apropriate settings of the filters and training parameters of the network is discussed. Connected components searching is used for improving the results. A classifier writen in C++ and OpenCV library is part of the work. The designed procedure is applied for segmentation of scanned scientific papers, but also the results of segmentation of more complex documents (advertisements, presentation slides) are presented.
|
|
|
Analysis of Ophthalmological Images Aimed to Diagnosis of Glaucoma
Vodáková, Martina ; Kolář, Radim (referee) ; Odstrčilík, Jan (advisor)
Bachelor thesis is focused on fundamental texture analysis of high-resolution fundus images aimed to subjectively and quantitatively describe properties of texture formed by the retinal nerve fiber layer. An area of interest was predefined in the form of ten sectors on each fundus image. The correlation between results of subjective and quantitative evaluation of the texture was monitored in each sector. The results show that proposed fundamental texture features are closely related to the subjective textural properties obtained from visual appearance of the retinal nerve fiber layer. The last step compares results from fundamental texture analysis with quantitative measurement of the retinal nerve fiber layer thickness provided by Optical Coherence Tomography.
|
|
|
Automation of Exoscopic Analysis Using Image Processing of Sedimentary Grains Acquired by Electron Microscope
Křupka, Aleš ; Křížek,, Marek (referee) ; Baroňák, Ivan (referee) ; Říha, Kamil (advisor)
This thesis deals with image analysis methods which can be exploited in exoscopic analysis of sedimentary grains, specifically for the purpose of distinguishing between geomorphologic geneses which influenced a form of sedimentary grains. The images of sedimentary grains were acquired by a scanning electron microscope. The main contribution is the proposal of multiple methods that can significantly automate the exoscopic analysis. These methods cover the automatic segmentation of grains in image, the automatic analysis of roundness of 2D grain projection and the classification of geomorphologic geneses according to the grain surface structure. In the section concerning the automatic segmentation, a segmentation method enabling an easy subsequent manual result correction was proposed. This method is based on the split-and-merge approach. The individual steps the procedure were designed to exploit specific properties of sedimentary grain images in order to obtain the best segmentation results. In the section concerning the automatic roundness analysis of 2D projection of sedimentary grains, an influence of pixel resolution on a result roundness value was evaluated. Further, a minimal number of grains, which is necessary to analyze in order to reliably compare a pair of geomorphological geneses, was investigated. For the determination of this number, a method was proposed and experimentally verified. In the section of automatic analysis of sedimentary grain surface structure, a method for classification of geomorphologic geneses was proposed. The method utilizes low-level texture features which describes individual images of sedimentary grains. A model of geomorphological genesis is constituted of a set of histograms representing occurrences of different configurations of low-level texture features. The methods proposed in the thesis were tested and evaluated based on a database, which consists of sedimentary grain samples from 4 different geomorphological geneses (eolic, glacial, slope and volcanic).
|
|
|
Analysis of retinal nerve fiber layer in fundus images utilizing local binary patterns
Doležal, Petr ; Harabiš, Vratislav (referee) ; Odstrčilík, Jan (advisor)
This work describes LBP (Local Binary Pattern) method in its various forms as a tool for distinguishing images with and without texture. The first part of the essay looks into the retinal nerve fiber layer, loss of the nerve fiber and especially into possibilities of retinal images with help of the fundus camera and into properties of this way received data. Second part of the essay describes and explains the LBP method which uses local binary operators for description of texture by help of histograms. From this way brought force of histograms is possible to gain a complex of features. Due to different classification approaches can then determine if new samples were selected from an image loss of retinal nerve fiber layer (RNFL). This solves the next part of the essay. And then is evaluated the correlation of features of LBP histograms of these images with the thickness of the RNFL in the same place. The methods described in this essay have been tested on a set of images in Matlab program and received results show, that the method can be useful for the diagnosis of glaucoma diseases.
|
|
|
Texture analysis of tumor tissue in lung CT data.
Šalplachta, Jakub ; Jan, Jiří (referee) ; Jakubíček, Roman (advisor)
The aim of this work is the revelation of the possibility of the use of texture analysis methods to detection and segmentation tumor tissue in lung CT image data and classification viable areas of tumor tissue. The main assumption of this thesis are differences of textural features between tumor and surrounding tissues and changes of these properties during development and treatment of this disease. The thesis contains overview of texture analysis methods. It deals with the creation of own method which is composed of some methods of texture analysis that create vector of properties (for each voxel in the image we get vector of features). This vector is afterwards processed by methods of cluster analysis. Content of this work is theoretical research of this issue, description of own method and statistical evaluation of the results. The method is processed in programming environment Matlab®.
|
|
|
Methods for texture analysis in ophthalmologic images
Hanyášová, Lucie ; Szabó, Zoltán (referee) ; Kolář, Radim (advisor)
This thesis is focused on texture analysis methods. The project contains an overview of widely used methods. The main aim of the thesis is to develop a method for texture analysis of retinal images, which will be used for distinction of two patient groups, one with glaucoma eyes and one healthy. It is observed that glaucoma patients don´t have a texture on the eye ground. Preprocessing of the images is found by transfer of the image to different color spaces to achieve the best emphasis of the eye ground texture. Co-occurrence matrix is chosen for texture analysis of this data. The thesis contains detail description of the chosen solutions and feature discussion and the result is a list of features, which can be used for distinction between glaucoma and healthy eyes. The method is implemented in Matlab environment.
|
|
|
Textural Analysis of Nerve Fibre Layer in Retinal Images
Novotný, Adam ; Jan, Jiří (referee) ; Odstrčilík, Jan (advisor)
This work describes completely new approach to detection of retinal nerve fibre layer (RNFL) loss in colour fundus images. Such RNFL losses indicate eye glaucoma illness and an early diagnosis of RNFL changes is very important for successful treatment. Method is presented with the purpose of supporting glaucoma diagnosis in ophthalmology. The proposed textural analysis method utilizes local binary patterns (LBP). This approach is characterized especially by computational simplicity and insensitivity to monotonic changes of illumination. Image histograms of LBP distributions are used to gain several textural features aimed to classify healthy or glaucomatous tissue of the retina. The method was experimentally tested using fundus images of glaucomatous patients with focal RNFL loss. The results show that the proposed method can be used in order to supporting diagnosis of glaucoma with satisfactory efficiency.
|
|
|
Analysis of Retinal Images Aimed to Nerve Fiber Layer Detection
Spáčil, Michal ; Kolář, Radim (referee) ; Odstrčilík, Jan (advisor)
Goal of this work is to theoretically develop and then program a system in Matlab environment to be used as a detection tool for layer of retinal neuron pathways . First part engages oneself upon the problem of analysis within spectral plane and results of using filters conceived upon statistical occurrences of certain frequencies in used samples. Second part than deals with use of gabor filters to detect neuron pathways and the statistical results gained by their use. Based on the results an analysis tool was programmed.
|
|
|
Texture analysis
Opletal, Tomáš ; Kratochvíla, Lukáš (referee) ; Honec, Peter (advisor)
Diploma thesis discusses texture analysis. Goal is to detect anomalies on the material, which could arise during process of making calenders on the nonwoven material. This thesis is using methods of Fourier transform with statistics and Neural networks to detect position of the missing calender.
|
guest ::
