|
|
A convolutional neural network for image segmentation
Mitrenga, Michal ; Petyovský, Petr (referee) ; Jirsík, Václav (advisor)
The aim of the bachelor thesis is to learn more about the problem of convolutional neural networks and to realize image segmentation. This theme includes the field of computer vision, which is used in systems of artificial intelligence. Special Attention is paid to the image segmentation process. Furthermore, the thesis deals with the basic principles of artificial neural networks, the structure of convolutional neural networks and especially with the description of individual semantic segmentation architectures. The chosen SegNet architecture is used in a practical application along with a pre-learned network. Part of the work is a database of CamVid images, which is used for training. For testing, a custom image database is created. Practical part is focused on CNN training and searching for unsuitable parameters for network learning using SW Matlab.
|
|
|
Experimental thermocamera measurements
Jakl, Oldřich ; Číp, Pavel (referee) ; Petyovský, Petr (advisor)
This work is focused on the features and the principles of the measuring of the thermovision cameras. There is the identification of the basic notions and physical laws on which is based the operation of the thermovision cameras in the first part of my work. In the second part there is describtion of the function of the detectors of infrared radiation and the character of the output data of the thermovision camera. Further there are presented the experiments and the observations which bring us closer to the features of the thermovision cameras and help us interpret the data gained by camera.
|
|
|
Image object detection
Pluskal, Richard ; Petyovský, Petr (referee) ; Richter, Miloslav (advisor)
The thesis deals with design of a program for entering various types of geometric objects in an image for the purpose of their further processing. The program should also contain algorithms to ease object entering (e.g. refining manually entered object position). In the first part there is a brief description of the computer vision and its basic methods used in the work as well as introduction of the OpenCV image processing library. The following part describes three types of geometric primitives that are implemented for now. Because the output of the program is in universal XML format, there is short chapter about the XML. After that, there are summarized some methods for searching of parametric description of geometric primitives in an image. The final chapter describes the proposed system and evaluates possibility and suitability of its usage for various types of images.
|
|
|
Traffic Situation Model
Dvořák, Michal ; Petyovský, Petr (referee) ; Horák, Karel (advisor)
In this thesis, parameters required for physical construction of model of traffic camera system are identified. The information is used to design and construct a model, which supports simulation of important traffic situations. With focus, on the ability of model to allow for digital modification of simulation parameters over, for this purpose created, communication interface. The next part of thesis then focuses on creation of application which supports the control and image retrieval from group of cameras. The application is designed to support settings necessary for use as average speed enforcement cameras and as red-light cameras.
|
|
|
Control of CNC mill
Cedrych, Jan ; Petyovský, Petr (referee) ; Macho, Tomáš (advisor)
In this thesis is discussed the possibility of upgrading the control system of mill MAHO MH 500 C with regard to current condition of the machine, planned use and owner financial capacity. The thesis also deals about connecting existing electrical equipment with a new control system. The proposed design allows simultaneous machining in three axes and positioning rotary table.
|
|
|
Scanning capillary column by color scanner and zones recognition
Wojnar, Petr ; Petyovský, Petr (referee) ; Štohl, Radek (advisor)
The master’s thesis focuses on creating an application for scanner control through WIA interface. This aplication is used for reading capillary during electrical separation methods in analytic chemistry. Scanned pictures of capillary are possible to process using online application for detection of significant zones within experiment. Offline detection of a set of scanned pictures is also possible. These applications have been created in LabVIEW environment made by National Instruments.
|
|
|
Image composition
Smital, Petr ; Petyovský, Petr (referee) ; Richter, Miloslav (advisor)
This thesis deals with methods of improving the quality of image output of an electron microscope by composing consecutive frames. The thesis contains a brief description of an electron microscope and the problems that deteriorate its image quality, and three basic mathematical algorithms that can be used to remove them. These are the simple averaging method, the method of least squares and the method of vector space. For all of the methods, the thesis describes ways of their implementation, the possibilities of their use and their mutual comparison. This thesis also deals with the problem of so-called superresolution, i.e. exceeding the physical resolution of a sensor using the methods mentioned above, and the problem of electron beam centring.
|
|
|
Detection of cellular processes in image sequences
Hatrinh, Hung Anh ; Richter, Miloslav (referee) ; Petyovský, Petr (advisor)
Překlad abstraktu (Tato bakalářská práce se zabývá segmentací buněk od obrazového pozadí a detekcí buněčných procesů v kvantitativních fázových obrazech získaných koherencí řízeným holografickým mikroskopem. Navržený algoritmus na segmentaci buněk využívá hranového detektoru watershedingu. Implemtován byl v programovacím jazyce C++ a využívá knihovny OpenCV. Detekce buněčných procesů je řešena metodami strojového učení v MATLABu.)
|
|
| |
|
|
Unary Classification of Image Data
Beneš, Jiří ; Petyovský, Petr (referee) ; Horák, Karel (advisor)
The work deals with an introduction to classification algorithms. It then divides classifiers into unary, binary and multi-class and describes the different types of classifiers. The work compares individual classifiers and their areas of use. For unary classifiers, practical examples and a list of used architectures are given in the work. The work contains a chapter focused on the comparison of the effects of hyper parameters on the quality of unary classification for individual architectures. Part of the submission is a practical example of reimplementation of the unary classifier.
|
guest ::
