|
|
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.
|
|
|
Costs of Running a Car Administration Android Application
Dorazil, Jan ; Široký, Vít (referee) ; Kubíček, Radek (advisor)
The bachelor thesis deals with mobile Android platform. The application for administration of costs of running a car was created within this thesis. It describes design and implementation of the application and analyses calculation of car's consumption and carbon dioxide emissions. The application uses SQLite database, asynchronous tasks and modern user interface components.
|
|
|
Automatic 3D segmentation of brain images
Bafrnec, Matúš ; Dorazil, Jan (referee) ; Kolařík, Martin (advisor)
This bachelor thesis describes the design and implementation of the system for automatic 3D segmentation of a brain based on convolutional neural networks. The first part is dedicated to a brief history of neural networks and a theoretical description of the functionality of convolutional neural networks. It represents a fast introduction to the problematics and provides theoretical basics needed for the understanding and creation of the system. Individual layers of the neural network and principles of their functionality and mutual relations are also described in this part. The second part of the thesis is about problem analysis, designing of a solution and a comparison between neural networks and other solutions. The result of a magnetic resonance imaging of the head is a series of black-and-white images representing a 3D scan. The task is to tag a brain and to remove unnecessary information in the form of surrounding tissues. The final image of the brain can be utilized in a volumetry or during a diagnostic of neurodegenerative diseases. The advantage of neural networks in comparison with deterministic systems is their flexibility. They allow an adaptation to other segmentation problems just by changing the training dataset, without a need of changes in the architecture. One of the systems performing fully automatic 3D segmentation is called U-Net – its name comes from the similarity of the architecture with the letter U. Three real solutions, the first implementation of U-Net, extended U-Net and recurrent U-Net were presented. The first version of U-Net has been very memory-demanding, it required a training on a processor instead of a graphic card and has not allowed data processing in full resolution. The extended U-Net has resolved these problems by loading data in overlaying series of three images. In addition to the possibility of a training on a graphic card with related decrease in learning time, the accuracy was increased by adding interconnections to the internal architecture of the network. The last version, recurrent U-Net, aims for the optimization of extended U-Net based on the reusage of existing levels. This brings a decrease in a time and resource difficulty. The number of parameters of the network was lowered to less than 20%, without any increase in case of further level addition. This network is one of first recurrent networks used on the problem of 3D segmentation and provides a foundation to further research. The last part focuses on the evaluation of results and the comparison of accuracy, speed and requirements between particular networks. The accuracy of human and machine segmentation is also compared. The extended and recurrent U-Net have surpassed their human opponent, which in real case could save a lot of doctors time and prevent human mistakes. The result of this work is a theoretical basis providing an introduction to the problematics of convolutional neural networks and segmentation, fully working systems for automatic 3D segmentation and the foundation for further research in the field of recurrent networks.
|
|
|
Tool for subjective quality evaluation of audiosignals restoration
Černý, Viktor ; Dorazil, Jan (referee) ; Záviška, Pavel (advisor)
Bacherol thesis deals with the theory of audio signal depreciation and reconstruction, with objective tests and subjective methods of reconstructed signal evaluation. At first, there are described several types of depreciation of audio signals and then reconstruction types for their reconstruction. After the reconstruction, types six objective and six subjective tests are mentioned for the evaluation of audio signal quality. The next part of the Bachelor thesis is the description of the program that was implemented in the programming language Java. The program is designed to design MOS, MUSHRA and ABX listening tests as well as to use for the actual testing. At the end of the thesis are the results of the listening tests that were used to test the program and the user ratings of the application.
|
|
|
Detection of changes in digital images
Dorazil, Jan ; Kříž, Petr (referee) ; Říha, Kamil (advisor)
This thesis concerns with change detection problematics in digital images captured under indoor conditions with an ordinary integrated camera in two consecutive moments. All challenges that accompany this problem will be discussed, starting with preprocessing and arriving to evaluation of the results. Currently used methods from this field are described and compared with each other such as differencing and LCP (Local Correlation Peak). A novel method, based on LTP descriptors, effectively solving this problem is proposed in this work. The proposed method is then tested on real data. The results of this tests are discussed subsequently. Besides the change detection method a method for parallax error minimization is proposed here.
|
|
|
Color Correction for 3D scanner and 3D printer
Kratochvíla, Michael ; Dorazil, Jan (referee) ; Říha, Kamil (advisor)
This thesis deals with color correction of a chain that starts with the 3D Artec MHT scanner, and ends with the 3D printers (CJP – Color Jet Printing technology). In principle, it is necessary to control the color interpretation of the entire chain from the scanning of real models to the 3D print model. With color properties and their color shade, including color textures. The principle of model surface scanning using a 3D scanner is in the same principle as photo camera which scans using a conventional CMOS chip. For this reason, color palettes were scanned using the photo camera and the resulting digital data were analyzed by the Darktable software. This analysis consisted of comparing the scanned color shades of the surface with the spectrofotometer measured data. The main goal of this method was to achieve color precision in the digital data during their acquirement, adjustment and interpretation. Then the same principle was applied to the data acquired by the 3D scanner to create an ICC profile of the 3D scanner. Because the 3D printer (CJP – Color Jet Printing) uses the same principle as the 2D printer, the 2D printing device calibration principle was used again to calibrate it. There have been defined procedures that adjust the color shade to the spectrophotometrically correct shades of the resulting print on a 3D printer. Color swatches were also printed for print quality verification. It has been found that with photo camera, which was used for objective measurement in the L*a*b* coordinates of independent space, any color setting and their adjustment is very sensitive to even small imprecisions. It has been found that it is not easy to obtain accurate colors within the Detla E
|
|
|
Object tracking in video sequence using the integral histogram
Přibyl, Jakub ; Kříž, Petr (referee) ; Dorazil, Jan (advisor)
This thesis focuses on object tracking in real-time. Tracked object is defined by bounding rectangle. The thesis works on issue of image processing and using histogram for real-time object tracking. The main contribution of the work is the extension of the provided program to track object in real-time with changing bounding rectangle. Size of the rectangle is changing as the object moves closer of further from camera. Furthemore the detection behavior in different scenarios is analyzed. In addition, various weight calculations were tested. The program is written in C++ using OpenCV library.
|
|
|
Segmentation of MR images using machine learning algorithms
Dorazil, Jan ; Mikulka, Jan (referee) ; Dvořák, Pavel (advisor)
This thesis concerns with magnetic resonance image segmentation using Random Forests algorithm. Employed technologies accomplishing the specified task include C++ progra- mming language with libraries ITK and OpenCV. This work descibes the technique of processing images from loading through preprocessing to the actual segmentation. The outcome from this work is a programme that automatically segmentates MR images of mouse’s head to the brain and the surroundings.
|
|
|
Wireless Sensor Networks Based on Mobile Devices
Dorazil, Jan ; Žák, Jakub (referee) ; Samek, Jan (advisor)
This master's thesis deals with the idea of using mobile devices as sensor nodes in wireless sensor network. Focused mostly on Android platform, we explore possibilities of wireless communication, and describe various types of sensors on mobile devices. We design and implement wireless sensor network based on mobile devices running Android operating system. The network performs real-time capturing of data from all sensors available and optionally from GPS. All measurements are visualized at the base station, which is Java Standard Edition desktop application. Wi-Fi, Bluetooth or even cellular internet can be used for communication within the network. Nodes can be remotely configured via SMS messages.
|
|
| |
guest ::
