|
|
Face detection and recognition with use of Raspberry Pi
Rozhoňová, Andrea ; Mézl, Martin (referee) ; Hesko, Branislav (advisor)
The following bachelor thesis is focused on the face detection and recognition in an image. The theoretical part divides methods of detection and recognition into several groups and there is better description and explanation of these methods in this part. At the end of the theoretical part is summarized the current utilization of person recognition on the bases of its face in practice. In the practical part is first implemented method for face detection. It is combination of two approaches - approach using haar features and approach using templates of eye. The face recognition is provided by the convolutional neural network. In conclusion there are summarized principles and problems associated with implementation on microcomputer Raspberry Pi and there is also evaluated the success of implemented methods.
|
|
| |
|
|
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.
|
|
|
HOUSE ON THE FOOTHILL - TOWN HOUSE IN THE HISTORICAL CENTRE
Veselá, Marie ; Rudiš, Viktor (referee) ; Oplatek, Jiří (advisor)
Potential sites lies not only in its location but also the dominant position it holds to their surroundings. Undeveloped plot represents a "node" or "island" ... loosening strictly linear character Bakery. It is a place which brings together three disparate streams - Classical serious at the running part of Mendel Square, dramatically quarreling upper section flowing into the area from Hus class and insignificant Anenská that, if there "just got lost." All "three" street, however, are closely connected with the plot and the transformation of space clearly indicates their transformation. A distinctive feature of the property is its visual exposure of looking from Mendel Square, the plot creates a "picture" to which the pawn closer. This image should be interesting, changing to attract one's attention for more than just one or two seconds. The image should not least communicate - what is happening on the ground, what links are individual objects ... a landmark and should, for use by infantrymen use. It should also not be attractive from a distance - when one zooms in close proximity, should be surprised by the discovery of something new, something that was not noticeable from a distance, it should be attention to detail, or idea that can be seen only at close contact.
|
|
|
Software for Microscope Image Processing and Analysis
Pavlišta, Libor ; Odstrčilík, Jan (referee) ; Čmiel, Vratislav (advisor)
This project informs about the basic image processing on grayscale and binary images. The project deals with analyzing the data obtained. Acquaints with terms such as morphology and image segmentation. Acquired knowledge is applied to create a program to complete the processing of microscopic images in LabView programming environment with subsequent analysis and plotting of results into image. For a better idea supporting data about operation in progress are continuous images.
|
|
|
Crowd-Sourcing Games for Annotations
Šujan, Tomáš ; Beran, Vítězslav (referee) ; Smrž, Pavel (advisor)
The goal of this bachelor thesis is to develop and implement a gaming application for the operating system Android, the purpose of which is to gather image annotations. The main purpose of this application is to simplify and improve this process, to extend the data range of these annotations and to provide entertainment for its users. The implementation of the application was processed in programming languages Android for the client segment and PHP for the server.
|
|
|
Image data shape analysis
Kylián, Jakub ; Harabiš, Vratislav (referee) ; Chmelík, Jiří (advisor)
Bachelor thesis is focused on shape analysis of image data. This thesis clarifies usage of methods, techniques and procedures that lead to such analysis. The content of this thesis is divided into three chapters – theory, analysis solution and conclusion. In the chapter theory, methods and general theory of the topic are introduced. The rule is, that every method used in subsequent sections is explained in detail, but this doesn't necessarily mean that it applies in reverse. Next chapter, following up the theory section is analysis solution. In this section, a problem is presented. This problem is then, with knowledge presented in chapter theory solved. The solution consists of many processes and preparations that are also explained in detail in this chapter.
|
|
|
Wavelet analysis and enhancement of MR tomography and ultrasound images
Matoušek, Luděk ; Bartušek, Karel (referee) ; Smékal, Zdeněk (advisor)
Tomographic MR (Magnetic Resonance) and sonographic biosignal processing are important non-invasive diagnostic methods used in a medicine. A noise added into processed data by an amplifier of tomograph receiving part and by circuits of sonograph is resulting in a body organ diagnosis degradation. Image data are stored in a standardized DICOM medical file format. Methods using wavelet analysis for noise suppression in image data have been designed and their comparation with classical methods has been made in this work. The MATLAB was utilized for data processing and data rewriting back to the DICOM format.
|
|
|
Design Manual as a Part of Marketing Communication
Šárková, Lenka ; Vaňous, Marek (referee) ; Mráček, Pavel (advisor)
This bachelor thesis deals with corporate identity, corporate design and subsequent design manual. It is divided into three parts. The first one summarizes the theoretical knowledge about marketing communication, corporate identity and design. The second part concentrates on the analysis of the current situation of corporate design in the company. Using all gathered information I created a design manual, which serves as a unification of the company’s visual image. Klíčová
|
|
|
Face Detection in Video
Kolman, Aleš ; Řezníček, Ivo (referee) ; Polok, Lukáš (advisor)
The project is focused on face detection in video. Firstly, it contains a summary of basic color models. Secondly, you can find the description and comparison of the basic methods for detection of human skin with a practical example of implementation of parametric detector. Thirdly, a theoretical basis for face detection and face tracking in a video containing a list of basic concepts and methods of this issue follows. Greater emphasis is placed on the description of machine learning algorithm AdaBoost and description of the possible application of the Kalman filter for the purpose of face tracking. Design, implementation and testing of library accomplished within the master thesis are listed in the final part of this thesis.
|
guest ::
