|
Measuring the thickness of contamination layers in scanning electron microscopy using image processing
Macek, Matěj ; Munzar, Milan (referee) ; Čadík, Martin (advisor)
Motivací pro vznik této práce byl cíl společnosti Thermo Fisher Scientific vyvinout metodu měření tloušťky kontaminačních vrstev na snímcích ze skenovací elektronové mikroskopie (SEM) pomocí pokročilých technik zpracování obrazu. Hlavním cílem je vytvořit automatizované metody pro kvantifikaci kontaminace v obrazech, které nepříznivě ovlivňují zobrazování ve výzkumu v oblasti materiálových věd, pomocí technik zpracování obrazu. V této studii shromažďujeme soubor dat snímků s kontaminací a ručně anotujeme masky pro každý snímek. Tyto anotace budou sloužit k doladění a vyhodnocení účinnosti námi navrhovaných metod. Použitím kombinace algoritmů detekce hran a modelů strojového učení, konkrétně vyladěné sítě DeepLabv3, tato práce zvyšuje přesnost a účinnost detekce kontaminace. Analyzátor kontaminace založený na detekci hran (EDCA) využívá tradiční metody zpracování obrazu, zatímco model DeepLabv3 zavádí přístup strojového učení, který robustně zvládá různorodé obrazové podmínky. Srovnávací analýzy prokazují účinnost těchto metod při poskytování spolehlivých, škálovatelných a podrobných měření kontaminačních vrstev, což významně přispívá k rozvoji oboru materiálových věd.
|
|
Measurement and Evaluation of Axis Straightness of Rotary Forgings using Photogrammetry and Image Analysis
Zatočilová, Aneta ; Druckmüller, Miloslav (referee) ; Matula, Pavel (referee) ; Morovič,, Ladislav (referee) ; Brandejs, Jan (advisor)
The thesis deals with methodology proposal for shape and dimension measurement of rotationally symmetric forgings. Most of available non-contact systems are not possible to use for this purpose, mainly due to high temperatures and large dimensions of forgings. Only a few commercial systems which are designed for this specific measurement are currently in the market. These systems are based on a principle of evaluating time response of posted modulated signal. However, scientific literature shows also other approaches to the measurement, which are based on principle of triangulation and methods of image analysis. Advantage of systems based on these principles should be especially measurement speed and significantly lower price. The paper describes current state of research and development in this area and proposes a new approach which is based on passive photogrammetry and image analysis. The core of the work is devoted to the design of partial methods and their implementation in the Matlab programming language. Functionality of the methodology and the software has been verified by measuring cylindrical tubes of small dimensions in laboratory conditions. The designed methods were discussed and evaluated based on statistical analysis of the measurement results, and further steps to increase the accuracy and reduce the spread of results were suggested. Optimization and further development of this methodology could lead to the design a professional measuring system intended for this specific application.
|
|
Neural Network Based Edge Detection
Janda, Miloš ; Žák, Pavel (referee) ; Švub, Miroslav (advisor)
Aim of this thesis is description of neural network based edge detection methods that are substitute for classic methods of detection using edge operators. First chapters generally discussed the issues of image processing, edge detection and neural networks. The objective of the main part is to show process of generating synthetic images, extracting training datasets and discussing variants of suitable topologies of neural networks for purpose of edge detection. The last part of the thesis is dedicated to evaluating and measuring accuracy values of neural network.
|
|
Analysis and segmentation of tomographic images
Dorazil, Jan ; Bartušek, Karel (referee) ; Smékal, Zdeněk (advisor)
The thesis deals with the edge detection in the magnetic resonance images and their segmentation. There are adduced the gradient based methods, methods based on zero-crossing in the Laplacian images and also methods combined both of the methods adduced above. These methods are compared to find the best one for the temporo-mandibular joint detection. Consequently sufficient segmentation method for particular parts of the temporo-mandibular joint (the condyle, the acetabulum and the articular disk) separation is chosen.
|
|
Line tracking for delivery robot
Juhas, Miroslav ; Horák, Karel (referee) ; Janáková, Ilona (advisor)
This thesis describes basics of methods and algorithms used in computer vision and application of them at a simple practical problem – line-tracking for delivery robot. The first part of this thesis contains basic theoretical knowledge of computer vision, which is important for understanding the problem. It is an introduction to problems of computer vision. The second part of thesis describes solving of particular steps, which are image preprocessing, segmentation, trajectory detection and algorithms for direction control. It contains outcomes of particular steps and selection of methods acceptable for solving the problem. There are presented experiences with tests of algorithms on the UTAR platform in context of this work. The last part of thesis is evaluating results taken during work.
|
|
Advanced Image Edge Detection
Novák, Marek ; Nečas, Ondřej (referee) ; Španěl, Michal (advisor)
Edge detection is one of the fundamental techniques used in the fields of image processing and computer vision. Goal of this thesis is an implementation and evaluation of chosen basic and advanced edge detection methods, including performance evaluation. Thesis describes implementation and performance evaluation of Linked Edges as Stable Region Boundaries method. Performance is evaluated using Berkeley Segmentation Data Set and Benchmarks 500 .
|
|
Text separation
Burlak, Vladimír ; Macho, Tomáš (referee) ; Richter, Miloslav (advisor)
This bachelor’s thesis describes basic methods of picture segmentation for the purpose of separation of text from a background. In first part are described general methods meant for picture processing. There is described verging, edge detection and interference reduction. In second part are defined categories of text in picture. Third part is focused on program which will help with picture segmentation.
|
|
The use of genetic algorithm for edge detection in medical images
Slobodník, Michal ; Švrček, Martin (referee) ; Hrubeš, Jan (advisor)
This work deals with the possibilities of employing a genetic algorithm to edge detection. There is introduced a project which uses enhanced image divided into sub-regions, on which detection by genetic algorithm is applied. To achieving our goals are used individuals in two-dimensional bit arrays, for which are specially adjusted mutation and crossover operators. Cost minimization approach is used as fitness function. The project was created and tested in Matlab environment.
|
|
Image analysis for correction of electron microscopes
Smital, Petr ; Schwarz, Daniel (referee) ; Kolář, Radim (advisor)
This thesis describes the physical nature of corrections of an electron microscope and mathematical methods of image processing required for their complete automation. The corrections include different types of focusing, astigmatism correction, electron beam centring, and image stabilisation. The mathematical methods described in this thesis include various methods of measuring focus and astigmatism, with and without using the Fourier transform, edge detection, histogram operations, and image registration, i.e. detection of spatial transformations in images. This thesis includes detailed descriptions of the mathematical methods, their evaluation using an “offline” application, descriptions of the algorithms of their implementation into an actual electron microscope and results of their testing on the actual electron microscope, in the form of a video footage grabbed from its control computer’s screen.
|
|
Image-Based Licence Plate Recognition
Vacek, Michal ; Hradiš, Michal (referee) ; Beran, Vítězslav (advisor)
In first part thesis contains known methods of license plate detection. Preprocessing-based methods, AdaBoost-based methods and extremal region detection methods are described.Finally, there is a described and implemented own access using local detectors to creating visual vocabulary, which is used to plate recognition. All measurements are summarized on the end.
|