|
|
Segmentation of optic disc in retinal image data
Juráček, Radek ; Mézl, Martin (referee) ; Odstrčilík, Jan (advisor)
This bachelor thesis is focused on the algorithm of automatic detection of the optical disk in retinal images. It briefly describes the anatomy of the human eye and the principles of scanning the ocular background. The following describes the optical disk segmentation methods. Selected methods are implemented in MATLAB and optimized using a genetic algorithm. A total of five methods were introduced and optimized on the HRF dataset and two experimental datasets.
|
|
|
Automatic detection of microcalcifications in mammogram images
Hývlová, Denisa ; Jakubíček, Roman (referee) ; Harabiš, Vratislav (advisor)
This bachelor thesis is focused on detection of microcalcification in mammography images. The introduction describes connection between their presence and breast cancer, principle of mammography and the DICOM standard used in radiology. In the following part the methods used for microcalcification enhancement and segmentation are explained. Detection algorithm based on wavelet transform, morphological closing and thresholding was designed in MATLAB. For evaluation of the results a graphical user interface was developed and an algorithm for automatic evaluation of the success rate in annotated mammography database was implemented.
|
|
|
Application of computational methods in classification of glass stones
Lébl, Matěj ; Hnětynková, Iveta (advisor)
Application of computational methods in classification of glass stones Bc. Matěj Lébl Abstrakt: The goal of this thesis is to employ mathematical image processing methods in automatic quality control of glass jewellery stones. The main math- ematical subject is a matrix of specific attributes representing digital image of the studied products. First, the thesis summarizes mathematical definition of digital image and some standard image processing methods. Then, a complete solution to the considered problem is presented. The solution consists of stone localization within the image followed by analysis of the localized area. Two lo- calization approaches are presented. The first is based on the matrix convolution and optimized through the Fourier transform. The second uses mathematical methods of thresholding and median filtering, and data projection into one di- mension. The localized area is analyzed based on statistical distribution of the stone brightness. All methods are implemented in the MATLAB environment. 1
|
|
|
Ecg Signal Quality Annotation
Waloszek, Vojtěch
This paper presents eight methods for extracting signal quality features and threshold based algorithm that evaluates the ECG signal quality. Each signal sample is classified into one of the three defined ECG signal quality classes.
|
|
|
Multi-Label Classification of Text Documents
Průša, Petr ; Očenášek, Pavel (referee) ; Bartík, Vladimír (advisor)
The master's thesis deals with automatic classifi cation of text document. It explains basic terms and problems of text mining. The thesis explains term clustering and shows some basic clustering algoritms. The thesis also shows some methods of classi fication and deals with matrix regression closely. Application using matrix regression for classifi cation was designed and developed. Experiments were focused on normalization and thresholding.
|
|
|
Segmentation of soft tissues in facial part of mouse embryos from X-ray computed microtomography data
Janštová, Michaela ; Harabiš, Vratislav (referee) ; Chmelík, Jiří (advisor)
This diploma thesis deals with a segmentation of soft tissues in facial part of mouse embryos in Matlab. Segmentation of soft tissues of mouse embryos was not fully automated and every case needs a specific solution. Solving parts of this issues can provide valuable data for evolutionary biologists. Issues about staining and segmentation techniques are described. On the basis of accessible literature otsu thresholding, region growing, k-means clustering and segmentation with atlas were tested. In the end of this paper are those methods tested and evaluated on 3D microtomography data.
|
|
|
Photo conversion to black and white
Pieger, Matúš ; Boštík, Ondřej (referee) ; Richter, Miloslav (advisor)
This bachelor's thesis describes the designing of algorithms for detection, processing and conversion of desired objects from input color images to grayscale or black and white domain. The input images are divided into two groups, where the first group consists of sudoku images and other brain puzzles. The second group contains images of paper documents. The thesis analyses imperfections of input images and their effect on the building and functionality of each of the programs. Subsequently, it looks for solutions of a reliable detection of desired objects and correction of their geometric distortions. For a better readability and toner saving when printing the output images respectively, the thesis gives answers as to how to erase unwanted shadows and in which way is it possible to perform bit depth reduction to a chosen number.
|
|
|
Application of computational methods in classification of glass stones
Lébl, Matěj ; Hnětynková, Iveta (advisor)
Application of computational methods in classification of glass stones Bc. Matěj Lébl Abstrakt: The goal of this thesis is to employ mathematical image processing methods in automatic quality control of glass jewellery stones. The main math- ematical subject is a matrix of specific attributes representing digital image of the studied products. First, the thesis summarizes mathematical definition of digital image and some standard image processing methods. Then, a complete solution to the considered problem is presented. The solution consists of stone localization within the image followed by analysis of the localized area. Two lo- calization approaches are presented. The first is based on the matrix convolution and optimized through the Fourier transform. The second uses mathematical methods of thresholding and median filtering, and data projection into one di- mension. The localized area is analyzed based on statistical distribution of the stone brightness. All methods are implemented in the MATLAB environment. 1
|
|
|
Segmentation on tomographic data of multiphase materials
Troják, Jan ; Šalplachta, Jakub (referee) ; Břínek, Adam (advisor)
This work deals with segmentation of multiphase materials from X-ray computed tomography measurement. The segmentation was performed on meteorite images. There are various intermetallic phases in the structure of the meteorite and they are difficult to separate. The main objective is to test different image processing techniques (Otsu's thresholding, cluster analysis, region growing). The techniques were chosen with the focus on their benefits for multiphase material segmentation. Image denoising and sharpening is used before segmentation. Subsequently, selected segmentation methods are applied to real data. The individual results are evaluated. Finally, the comparison of selected methods is presented.
|
|
|
Blood vessel tree segmentation of the mouse liver in CT data
Smékalová, Veronika ; Odstrčilík, Jan (referee) ; Kolář, Radim (advisor)
The methodology of visualization of soft tissue is in biology and medicine a topic for many years. During this period there were approving many techniques how to achieve accurate and authentic image of the researched object or structure. X-ray computed tomography is very helpful to get this goal but is necessary to improve contrasting techniques as well as the techniques of image post-processing. This thesis deals with imaging soft tissue. Specifically, it focuses on mouse liver contrasting with the artificial resin Microfil. Thesis also describes image processing technique (thresholding and region growing) for the data of the measurement with the goal of the visualization of the sample in 3D.
|
guest ::
