National Repository of Grey Literature 51 records found  beginprevious32 - 41next  jump to record: Search took 0.00 seconds. 
QR code detection under ROS implemented on the GPU
Hurban, Milan ; Věchet, Stanislav (referee) ; Krejsa, Jiří (advisor)
Tato diplomová práce se zabývá vývojem a implementací algoritmu pro detekci QR kódů s integrací do platformy ROS a výpočty běžícími na grafické kartě. Z rešerše současně dostupných nástrojů a technik je vybrán vhodný postup a algoritmus je napsán jako modul v programovacím jazyce Python, který je snadno integrovatelný do ROS. Ke zprostředkování výpočtů na vícejádrovém hardware, jako jsou grafické karty či vícejádrové procesory, je využita knihovna OpenCL.
Analysis of videokymographic images
Zita, Aleš ; Zitová, Barbara (advisor) ; Novozámský, Adam (referee)
In ongoing basic human vocal chord functionality research, scientists try to describe the dependency of the glottal wave characteristics on tone generation and vocal chord properties. One of the affordable vocal chord visualization techniques for clinics is the Videokymography - technique based on recording the vocal chord vibration using a CCD camera modified to a line-scanner. Recorded rows are than combined to form a spatial-time recording. These records are suitable for computer based extraction of the vocal chord characteristics, including the characteristics of the glottal waves. In this thesis the method for automatic detection of the glottal waves was developed and implemented utilizing the digital image processing techniques. The proposed method is primarily focused on processing the healthy vocal chords videokymographic images as they gives us a good reference for the physiology of the human vocal chord organ.
Data extraction from document scans
Macháč, Bohuslav ; Kolomazník, Jan (advisor) ; Krajíček, Václav (referee)
In this work I developed an application capable of extracting data from scanned documents. For optical character recognition, I used external OCR engine Tesseract, but it can be easily changed. I use document templates, which have informations about data areas and its data types. I tried to automatize most of the steps which are required to extract data or create new data template. User can improve or change results of these steps. For export from application I implemented components, which export data to XML, HTML or plain text. Another components can be easily added, to adapt application for various uses.
System for Automatic Parking Access Based on License Plate Recognition
Václavek, Patrik ; Sochor, Jakub (referee) ; Špaňhel, Jakub (advisor)
Goal of this thesis was to design and implement system operating in real time, which manages to detect incoming vehicle to the car park terminal, recognize its licence plate and automatically decide on its admission. System uses the Gaussian Mixture Model algorithm for detection of incoming vehicle. For reliable localization of licence plate are used two methods, the first one uses of extraction of Maximally Stable Extremal Regions (MSERs), the second one uses of Top-Hat transformation. Support Vector Machine (SVM) algorithm is used to decide, whether is the found area a licence plate. Character classification is performed using artificial neural network. For implementation was used library OpenCV. Thanks to optimalization is the extraction of MSERs accelerated up to seven times. The accomplished success rate in case of licence plate localization is 92,47% and in case of classification of characters is 90,03%. 
Effects of Defects on Composite Structures Load Carrying Capacity: Delaminations at a Bi-Material Interface
Matěják, Vladimír ; Kotoul, Michal (referee) ; Růžička, Milan (referee) ; Juračka, Jaroslav (advisor)
Kompozitní materiály se projevují komplexním způsobem porušování, které může být dále ovlivněno přítomností různých poruch plynoucích z výrobních processů nebo se vyskytujících v průběhu života součásti. Důkladné porozmění procesů porušování a jejich okolností je nezbytné pro navrhování kompozitních konstrukcí, jenž budou bezpečnější, trvanlivější a ekonomičtější. V první části disertační práce jsou popsány způsoby porušování kompozitů a uvedeny současné matematické metody pro analýzu a výpočet únosnosti. Dále jsou zde vyjmenovány hlavní druhy vad a stručně diskutován jejich vliv na vlastnosti kompozitních materiálů. Zvláštní důraz je kladen na delaminace, společně se základními principy lomové mechaniky a jejich uplatnění při výpočtech a zkoušení kompozitů. Druhá část je zaměřena na delaminace na rozhranní dvou různých materialů. Lomová houževnatost byla experimantálně měřena ve třech typech zatížení za účelem stanovení poruchového kritéria založeného na podílu módu I a módu II. Během tohoto experimentu byla vyvinuta nová metoda měření délky trhliny pomocí digitáního zpracování obrazu a rovněž byla navržena nová definice počátku šíření trhliny. Analytické vztahy pro výpočet míry uvolnění deformační energie z naměřených dat byly rozšířeny o vliv rozdílných elastické parametrů materiálů na rozhranní. Podrobnější prozkoumání analytických vztahů a výpočet metodou konečných prvků odhalil, že podíl módu I a módu II je závislý na vzdálenosti od čela trhliny a poruchové kritérium založené na podílu smíšenosti tak nemůže být použito.
Processing of cardiac cell images
Václavek, Martin ; Čmiel, Vratislav (referee) ; Odstrčilík, Jan (advisor)
This bachelor thesis is dealing with topic of digital image processing in the field of cardiac cell imaging. The aim of this thesis is familiarization with cardiac cell imaging methods and then with methods of digital image processing for a purpose of cardiocyte contractility analysis of previously captured image sequences. Basic methods of image processing and principles, which they are based on, are described. Methods for assessing cardiocyte contractility are also described. In the following part, chosen methods are implemented in MATLAB® and applied on two image sequences of cardiac cells, which were obtained using bright field microscopy.
Adaptive image sharpening
Jakubíček, Roman ; Odstrčilík, Jan (referee) ; Jan, Jiří (advisor)
This thesis is the analysis of the problem and technical report that supports a computer program for enhancement image. The main objective of picture processeng is adaptive sharpening, which is obtained by the application of a local convolutional operator. The decision on the degree of sharpening at individual pixels is based on the value of the local standard deviation of brightness. The degree of sharpening can take binary or continuous values. The first part of the report briefly discusses the theory of adaptive image sharpening. Knowledge of this theory is necessary for understanding the remaining chapters, which describe the individual algorithms including flows-diagrams, implementation of the program and graphical enviroment and also assess the achieved results, including demonstration on examples. The last section of the report deals with variability of images and it’s influence on settings parameters of sharpening.
Recognition of Hits in a Target
Semerák, Vojtěch ; Dittrich, Petr (referee) ; Drahanský, Martin (advisor)
This thesis describes two possible ways of hit recognition in a target. First method is based on frame differencing with use of a stabilization algorithm to eliminate movements of a target. Second method uses flood fill with random seed point definition to find hits in the target scene.
Coevolutionary Algorithm in FPGA
Hrbáček, Radek ; Vašíček, Zdeněk (referee) ; Drahošová, Michaela (advisor)
This thesis deals with the design of a hardware acceleration unit for digital image filter design using coevolutionary algorithms. The first part introduces reconfigurable logic device technology that the acceleration unit is based on. The theoretical part also briefly characterizes evolutionary and coevolutionary algorithms, their principles and applications. Traditional image filter designs are compared with the biologically inspired design methods. The hardware unit presented in this thesis exploits dual MicroBlaze system extended by custom peripherals to accelerate cartesian genetic programming. The coevolutionary image filter design is accelerated up to 58 times. The hardware platform functionality in the task of impulse noise filter design and edge detector design has been empirically analyzed.
OPTIMIZATION OF THE HYDRAULIC SYSTEMS PROJECT IN TERM OF TIME CHANGE OF PARAMETERS
Hudec, Martin ; Haluza, Miloslav (advisor)
The objective of this project was to contribute to deepen the piece of knowledge about swi¬rling movement of the water in the hydraulic power plants’ water intakes, especially in case of the Swirl Turbine. The vortexes mostly occur near outflow holes in the bottom or walls of water tanks. Collectively they are called inflow vortices. According to the form they take they can be divided into four main categories. By the model research on hydraulic power plants’ inflow it is generally concerned on determination enough infallible conditions, under which the pulling-in of the air by a vortex into an inflow does not happen. For this purpose has been in the Fluid engineering laboratory projected and realized an experimental device enabling observation of creation, spread and extinction of the inflow vortices.

National Repository of Grey Literature : 51 records found   beginprevious32 - 41next  jump to record:
Interested in being notified about new results for this query?
Subscribe to the RSS feed.