|
|
Mobil Application Support for Nine Men's Morris Playing
Kolínek, Daniel ; Zbořil, František (referee) ; Zbořil, František (advisor)
The aim of this work is to create an application for mobile device solving the task of determination the best move in game Nine men's morris from a camera snapshot taken on smart device. The task is divided into the problem of position detection and determination of the best move. Position recognition is solved by using edge detection, finding circles using Hough transform and subsequent color detection in found circles. Finding the best move is solved by own position evaluation and state space search using the Alpha-Beta algorithm. Using the OpenCV library and the Android Studio development environment, a sample application executable under Android version 5 and higher was created. The sample application solves both tasks.
|
|
|
Smoke and Fire Detection in Video Sequences
Tomek, Peter ; Štancl, Vít (referee) ; Švub, Miroslav (advisor)
This thesis aims to analyse a videosignal given in input and find segments that contains fire or smoke. The problem is divided into two cases-detection of fire and detection of smoke. The first and main step of analysation is detection of segments by Gaussian mixture model that is trained by Expectation-Maximization algorithm, or shortly EM algorithm. For smoke detection is than used method of optical flow. The final segments are than processed by some morphological methods and determination of their position is made. Finally, the output of algorithm is again a videosignal in which segments that probably contains fire or smoke are highlighted.
|
|
|
Recognition of persons clothing in the video signal
Mlýnková, Barbora ; Kříž, Petr (referee) ; Přinosil, Jiří (advisor)
This paper is dealing with the detection clothes characteristics in the picture, for the use of person identification. These characteristics are described and categorized. It also deals with the design of the database structure, which works with masks and categories of characteristics for their processing. This work uses haar cascades to detect face and to determine the position of clothing for the purpose of color detection
|
|
|
Neural Network Based Edge Detection
Jamborová, Soňa ; Grézl, František (referee) ; Švub, Miroslav (advisor)
This work is about suggestion and implementation of the software for detection of edges in images using neurons network. It defines basic terms for this topic and focusing mainly at preperation imaging imformation for detection using nerons network. Describing and comparing different aproachings for using implemented software on synthetic and real set of images, including experiments.
|
|
|
Code Detection from Control Image
Růžička, Miloslav ; Zuzaňák, Jiří (referee) ; Beran, Vítězslav (advisor)
Work deals with code detection from control image. The document presents relevant image processing techniques dealing with a noise reduction, thresholding, color models, object segmentation and OCR. This project examines advantages and disadvantages of two selected methods for object segmentation and introduces developed system for object segmentation. The developed system for object segmentation and classification is realized, evaluated and results are discussed in details.
|
|
|
Software for data hiding in image files
Morkus, Filip ; Říha, Kamil (referee) ; Burda, Karel (advisor)
In my master's thesis I start fromthedescriptionofthebasics and thebeginningsofsteganography, itsmethods and purposes. Detaileddescriptionof BMP fileswithhidden data follows. A filestructureisanalysedintothesmallestdetails to avoiddamagingfilewhilehiding. At thesametime to make profit oftheinformationincluded in a fileheader in the most effectiveway. Anotheraimwas to explain a principalofsteganographicalmethoditself, usedforhiding data into BMP file. Based on these findings, a programmeconceptwasdesigned and consequentlythatprogrammewas made. Itcarriesoutthehiding and revealing data intothe image files. Directionsfor use are made to thisprogramme and thereisalso a demo ofthefeaturesdescribingeach step. At the end ofmymaster's thesis anattentionispaid to thoseinfluencesthatcanbelimitingforthismethod. Exceeding these limitswouldlead to breakingthesteganographicalmethod, whichmeansrevealingthehidden data.
|
|
|
Impact of color models on performance of convolutional neural networks
Šimunský, Martin ; Doležel, Petr (referee) ; Škrabánek, Pavel (advisor)
Current knowledge about impact of colour models on performance of convolutional neural network is investigated in the first part of this thesis. The experiment based on obtained knowledge is conducted in the second part. Six colour models HSV, CIE 1931 XYZ, CIE 1976 L*a*b*, YIQ a YCbCr and deep convolutional neural network ResNet-101 are used. RGB colour model achieved the highest classification accuracy, whereas HSV color model has the lowest accuracy in this experiment.
|
|
|
Interactive web applications for education of color theory
Koroleva, Anfisa ; Přinosil, Jiří (referee) ; Rajmic, Pavel (advisor)
This bachelor thesis deals with the issue of interpretation of colors and color images in computer graphics. Specifically, the work is focused on the development of simple web applications – applets that will serve for interactive submission of methods used in the field of computer processing of color images. The created applets should demonstrate the relevant theory relating to color mixing in different color models, conversion of a color image to a gray-scale image, conversion of a gray-scale image to a false-color image, conversion of physical light into CIE XYZ and L*a*b* color spaces. The first part of the thesis describes the theoretical basis for the required applets. The following practical part is dedicated to the process of implementing the applets using JavaScript and HTML.
|
|
|
Image codecs based on the wavelet transform
Kiska, Tomáš ; Říha, Kamil (referee) ; Rajmic, Pavel (advisor)
This bachelor´s thesis describes issues of wavelet compression, which is today already in common use mainly at work with digital photographs or other pictures. Using these algorithm you can copy informations and save efficiently. There are main image formats and types of compression suitable for editing pictures desribed in this thesis. So the focus is on discrete wavelet transform, which uses so-called wavelets, the Haar´s and Daubechies wavelet are the best known of all. Next chapter of this work explores colour spaces, in which can be a picture displayed. In case of coding and encoding it is model RGB and YCbCr. Not least there is mentioned term of picture decomposition. At the end, there are image codecs EZW, SPITH and EBCOT which are describe in detail.
|
|
|
RGB MATRIX LED system
Sikora, Roman ; Fedra,, Zbyněk (referee) ; Hudcová, Lucie (advisor)
The bachelor thesis deals with the development of a control software for the rear RGB LED lamp, which allows to design and display any color schemes. The first part of the work aims at development of complete Raspberry Pi 3 control software. Next thing which the thesis deals with is design of user interface for Windows platform for easy creation of color schemes which includes typical functions for a rear lamps like a tial, stop, reverse, fog, direction indicator, coming home and leaving home. Next part of the work is implementation of the control for the model via CAN bus which is used in automotive technology, and to develop the control software for Windows platform. In the project the whole model with Raspberry Pi is tested for Conducted emissions.
|
guest ::
