|
|
Real-Time Liquid Lens Focusing
Zaťovič, Martin ; Drahanský, Martin (referee) ; Rydlo, Štěpán (advisor)
Rýchlosť zaužívaného prístupu k zaostrovaniu kamerových systémov naráža na úzke hrdlo - mechanický pohyb motora, ktorý mení vzdialenosť šošovky od obrazového snímača kamery. Technológia tekutej šošovky sľubuje riešenie tohto problému elimináciou potreby mechanického pohybu. Systémy ktoré ju využívajú sú teda podstatne zrýchlené. Cieľom tejto práce je potvrdenie, alebo vyvrátenie týchto tvrdení a v prípade ich potvrdenia zistiť do akej miery je tekutá šošovka schopná zrýchliť systémy, ktoré ju využívajú. Pre testovanie zrýchlenia implementujeme automatické zaostrenie na základe spracovania obrazu a spustíme ho na kamerových systémoch, ktoré využívajú tekutú a elektromechanickú šošovku. Automatické zaostrovanie na základe spracovania obrazu počíta skóre ostrosti zhotovených obrázkov a hľadá jeho maximum pri rôznych hodnotách zaostrenia.
|
|
|
Detection, Extraction and Measurement of the Length of the Metacarpal Bones in Images
Ulej, Vojtěch ; Rydlo, Štěpán (referee) ; Drahanský, Martin (advisor)
The aim of this bachelor thesis is to study the literature dealing with the topic of object (specifically bones) recognition in images. Another task is to summarize the existing solutions for detection and measurement of object's length and to design a suitable algorithm for detection and measurement of metacarpal bones in images. First proposed algorithm is based on edge detecting methods. However, this approach has proved unreliable. The second algorithm design is based on machine learning using the convolutional neural network Mask RCNN.
|
|
|
Detection, Extraction and Measurement of the Length of the Metacarpal Bones in X-Rays of the Human Hand
Chalupnik, Alexandr ; Rydlo, Štěpán (referee) ; Drahanský, Martin (advisor)
The aim of the bachelor thesis is the design and implementation of an algorithm for the detection, extraction and measurement of the length of the metacarpal bones in x-rays of the human hand. The first part is focused on the principles of x-rays and the anatomy of the human hand. The second part contains the design and implementation of the task. The algorithm is based on image processing methods, such as thresholding or edge detection. In the end, the measurement results are evaluated on a set of images, which were provided by the Department of Anthropology at Masaryk University.
|
|
|
Editor for WSQ Format of Fingerprint Images for Demonstration
Németh, Patrik ; Rydlo, Štěpán (referee) ; Kanich, Ondřej (advisor)
The goal of this thesis is to design and implement an application suitable for demonstrating the individual steps of fingerprint analysis, and which is able to automatically process fingerprints stored in the most widely used formats for storing fingerprint imagery, such as WSQ, PNG and JPEG 2000. In this thesis special attention was given to automatic processing methods and analysis of fingerprint imagery. It also offers an overview of the WSQ format and of its comparison to JPEG 2000. The output of this work is a graphical application capable of demonstrating individual steps of widely used methods of fingerprint imagery processing and analysis. The application implements Gabor filtering, line thinning based on the Zhang-Suen method, and other methods of fingerprint processing. With some error, it is capable of detecting minutiae, singularities and the class of a fingerprint. Some of the processing parameters may be modified by the user via the graphical interface. Processed images can be exported in various image formats.
|
|
|
Detection and Classification of Damage in Fingerprint Images Using Neural Nets
Vican, Peter ; Rydlo, Štěpán (referee) ; Kanich, Ondřej (advisor)
The aim of the diploma thesis is to study and propose improvement of the current convolutional neural network for the classification and detection of fingerprint disease. An improvement of the current convolutional neural network is the change of library for the algorithm of learning, detecting and classifying fingerprint damage. Other improvements are to change the convolutional neural network model and a change in the activation function. At the same time, preprocessing using the Gabor filter will be added. Another change is in the area of thresholding. Next, there will be a change in general-purpose algorithms that will simplify the work for expanding database creation, the learning process itself, the classification and detection process, and the network testing process. At the same time, this network will be expanded with a new prediction and classification. Specifically the damage caused by eczema, psoriasis, pressure and moisture. The improved convolutional neural network is implemented by PyTorch. The network detects which part of the fingerprint is damaged and draws this part into the fingerprint. At the same time, the type of disease or imprint damage is classified during detection. Synthetic fingerprints are used in network training and are supplemented by real fingerprints.
|
|
|
Information system for the administration of student guild
Halabica, Michal ; Rydlo, Štěpán (referee) ; Dytrych, Jaroslav (advisor)
This thesis deals with the creation of a central information system for student associations. The goal of this thesis is to create a system, that will ease everyday work in the student association. The created solution is based on requirements of the FIT BUT Student Union, which were adapted for the possibility of use by other student associations. The information system was implemented as web application using .NET technologies with C# language and Angular with TypeScript language. The final version was tested by members of the already mentioned student union.
|
|
|
Detection of a Drone in Space
Rydlo, Štěpán ; Orság, Filip (referee) ; Drahanský, Martin (advisor)
This master thesis purposes is create localization system using software defined radio. The purpose of this thesis is to create new localization system, which will be independent of existing systems. To create a localization system, we will use ADALM-PLUTO device to send and receive radio signals. This work contains a decription of serval possibilities how to create the localization system and description of their comunication.
|
|
|
Real-Time Object Localization
Rydlo, Štěpán ; Chudý, Peter (referee) ; Kolář, Dušan (advisor)
This bachelor thesis purposes solution of a radio signal processing to determine actual receiver position on computers using software defined radio. The purpose of this thesis is to create and parallelize program to achieve real-time processing . To achieve real-time processing we will use GPU . This work contains a description of two independent possibilities of data transfer and processing .
|
|
|
Car Movement Measurent on Carrera Racing Tracks
Šíma, Vojtěch ; Malaník, Petr (referee) ; Rydlo, Štěpán (advisor)
The aim of this bachelor thesis is to design a measuring device that allows to measure quantities such as speed, acceleration and centripetal force while the car is moving on the Carrera racetrack. An embedded system will be created for measurement, where the main result is a printed circuit board that was created and mounted according to a schematic design composed of currently available electronic components. As the board moves along the race track, data is then recorded based on the implemented program, which is stored on a memory medium and later processed for a suitable visual presentation. Based on this data, it is then possible to analyse how the model behaves when moving on the autotrack and which factors have an effect on this movement.
|
|
|
System for Long-Term Measurement of Patient Pressure
Petrovič, Michal ; Rydlo, Štěpán (referee) ; Drahanský, Martin (advisor)
The goal of this thesis is to create an algorithm to model the peak flux of patients at cardiology clinics to improve the handling time per patient by the doctors. The focus of the project was to improve the retrieval, processing and displaying of patient's blood pressure results to a doctor. To tackle this problem, a computer program was written that automatically downloads the relevant blood pressure data, analyses it and presents it to the attending doctor. The developed application includes the possibility to monitor the blood pressure over a selected time interval, interpreting the results and recognize arrhythmia. The proposed solution simplifies the patient's life, decreases the waiting time for the attending doctor and thus increases his efficiency.
|
guest ::
