|
|
Speckle noise suppression
Kuchař, Otakar ; Hesko, Branislav (referee) ; Mézl, Martin (advisor)
Master thesis deals with the study of ultrasound. The first part of this work is devoted to basic physical principles, imaging modes, ultrasound probes, biological effects and the last part is associated with the artifact associated with ultrasound waves. In the next part the specific noise called speckle noise is detaily discussed. The description includes both a mathematical and a statistical view. Several methods are described to eliminate this noise. In the practical part the described methods are realized and compared based on objective and subjective evaluation.
|
|
|
Text recognition with artificial neural networks
Peřinová, Barbora ; Hesko, Branislav (referee) ; Mézl, Martin (advisor)
This master’s thesis deals with optical character recognition. The first part describes the basic types of optical character recognition tasks and divides algorithm into individual phases. For each phase the most commonly used methods are described in the next part. Within the character recognition phase the problematics of artificial neural networks and their usage in given phase is explained, specifically multilayer perceptron and convolutional neural networks. The second part deals with requirements definition for specific application to be used as feedback for robotic system. Convolution neural networks and CNTK library for deep learning using algorithm implementation in .NET is introduced. Finally, the test results of the individual phases of the proposed solution and the comparison with the open source Tesseract engine are discussed.
|
|
|
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.
|
|
|
Therapeutic game implementation with use of EMG signal
Drozd, Tomáš ; Kolářová, Jana (referee) ; Hesko, Branislav (advisor)
This bachelor thesis describes electromyography which we can use for biofeedback. At first, it describes electromyography and methods of measuring. Then biofeedback is described and its usage for therapeutic purposes or therapeutic games. Also it introduces BITalino device which represents low-cost solution for biofeedback. For practical uses there is provided a program written in C++ which includes Super Mario World. Appliation also draws measuered signal and parameteres calcuted from it.
|
|
| |
|
| |
|
|
Simulation of ultrasound sequences in contrast mode
Staňková, Jana ; Hesko, Branislav (referee) ; Harabiš, Vratislav (advisor)
This bachelor thesis deals with the principle of contrast imaging techniques for ultra-sound imaging. In the first part there are described basic principles and characteristics of ul-trasound waves for the understanding. It is also focused on ultrasound contrast agents used in contrast enhanced ultrasound imaging. The important part is the description of perfusion mo-dels with a focus obtain perfusion parametres and analyze perfusion curves obtained by mea-suring the ultrasound contrast agent over time. The second part is devoted to designing a pro-gram for generating simulated ultrasound images and description of the simulation of 2D ul-trasound tomograms.
|
|
|
Simulation of ultrasound sequences in contrast mode
Staňková, Jana ; Hesko, Branislav (referee) ; Harabiš, Vratislav (advisor)
This bachelor thesis deals with the principle of contrast imaging techniques for ultra-sound imaging. In the first part there are described basic principles and characteristics of ul-trasound waves for the understanding. It is also focused on ultrasound contrast agents used in contrast enhanced ultrasound imaging. The important part is the description of perfusion mo-dels with a focus obtain perfusion parametres and analyze perfusion curves obtained by mea-suring the ultrasound contrast agent over time. The second part is devoted to designing a pro-gram for generating simulated ultrasound images and description of the simulation of 2D ul-trasound tomograms.
|
|
|
Automatic Classification of Antibiotic Discs Photographs
Hesko, Branislav ; Kolář, Radim (referee) ; Walek, Petr (advisor)
This bachelor’s thesis deals with problematics of automatical classification of antibiotical discs photographies.The aim of this work is to apply several methods on images to create output with classified images. The problem is split into preprocessing and classification by itself. Preprocessing is solved with the use of Canny’s edge detector, Hough transform for detecting lines and circles, alignment, rotation and cutting out text with individual letters. Classification is then realised using neural network and minimum distance between pixels. Explanations and analysis of this methods should help to create theoretical overview on analysed problematics. The application of these algorithms in practical part will show some persisting imperfections of choosen processing caused by low quality of photographies of antibiotical discs.
|
|
|
Ultrasound image registration based on active contours
Hesko, Branislav ; Jakubíček, Roman (referee) ; Harabiš, Vratislav (advisor)
This diploma thesis aims to implement an active contour method for ultrasound image segmentation. Properties of ultrasound images, basic segmentation approaches and a~principle of choosen active contour methods are described within theoretical part. Two different groups of active contour methods exists, methods with use of gradient and without use of gradient as image feature. For comparision, one method of each group is implemented in practical part and subsequently, segmentation efficiency and properties of methods are compared in evaluation part.
|
guest ::
