|
| |
|
|
Acceleration of 3D Image Processing Using GPU
Kozovský, Radoslav ; Klepárník, Petr (referee) ; Španěl, Michal (advisor)
p { margin-bottom: 0.21cm; direction: ltr; color: rgb(0, 0, 0); line-height: 150%; }p.western { font-family: "Times New Roman",serif; font-size: 11pt; }p.cjk { font-family: "Times New Roman",serif; font-size: 11pt; }p.ctl { font-family: "Times New Roman",serif; font-size: 12pt; } The aim of this work is to accelerate the calculation of selected 2D and 3D image filters using GPU using OpenCL. Specifically, it deals with the implementation and comparison of various variants of Sobel's edge detector and Gauss filter using global or local memory. Acceleration has been achieved on 3D filter variants. On 2D filter variants, the overhead for data transfer to and from the GPU was too high.
|
|
|
Image Database Query by Example
Dobrotka, Matúš ; Hradiš, Michal (referee) ; Veľas, Martin (advisor)
This thesis deals with content-based image retrieval. The objective of the thesis is to develop an application, which will compare different approaches of image retrieval. First basic approach consists of keypoints detection, local features extraction and creating a visual vocabulary by clustering algorithm - k-means. Using this visual vocabulary is computed histogram of occurrence count of visual words - Bag of Words (BoW), which globally represents an image. After applying an appropriate metrics, it follows finding similar images. Second approach uses deep convolutional neural networks (DCNN) to extract feature vectors. These vectors are used to create a visual vocabulary, which is used to calculate BoW. Next procedure is then similar to the first approach. Third approach uses extracted vectors from DCNN as BoW vectors. It is followed by applying an appropriate metrics and finding similar images. The conclusion describes mentioned approaches, experiments and the final evaluation.
|
|
|
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.
|
|
|
Convolutional Networks for Lip Reading
Kadleček, Josef ; Kišš, Martin (referee) ; Hradiš, Michal (advisor)
This thesis deals with current methods for automatic speech recognition and lip reading via neural networks. Furthermore it deals with similarities in the architectures of neural networks for audio and visual data and available datasets in the field of audiovisual automatic speech recognition. The main contribution of this thesis is set of experiments comparing different changes in neural network architecture and its impact on results. The thesis includes an implementation of a system for automatic speech recognition from audio (CER: 12.6 %) and visual (CER: 57,7 %) data. The architectures of both systems are based on features extraction via convolutional networks followed by recurrent layers LSTM, another layer of convolutions and loss function CTC.
|
|
|
Time-Gathering Video
Kárníková, Pavlína ; Sumec, Stanislav (referee) ; Herout, Adam (advisor)
This bachelor essay describes problems of creating time-gathering video, image processing and the theory of photography. Purpose is created program, which can modify photos and after that create video. Program is implemented in the C and C++ language and uses the OpenCV library. Application can run in the operation system Windows.
|
|
|
Set of Web-Based Demonstrations for Signal Processing
Kaňok, Tomáš ; Jančík, Zdeněk (referee) ; Černocký, Jan (advisor)
The aim of this bachelor's thesis is to give a basic overview about convolutions and complex exponential functions used in signal processing. Additionally, it contains the list of existing public educationally-oriented solutions available on the Internet. Set of web-based demonstrations for signal processing is proposed, implemented and evaluated upon analyzed solutions.
|
|
|
Data acquisition and processing in LabVIEW
Kroliczek, Filip ; Havránek, Zdeněk (referee) ; Šedivá, Soňa (advisor)
The thesis deals with data collecting and treating issues utilizing the help of the LabVIEW software. An overview is presented on the first pages. Following chapters are dedicated to theoretical analysis of convolution, correlation, fast Fourier transformation and harmonic distortion of signal. Theoretical analysis of the function with of signal treatment precedes an introduction to LabVIEW – a programme for measurement and treatment of signal. The subsequent chapter describes a LabVIEW created measuring function, program settings and description of a chosen part of the programme. The end comprises the evaluation of the elaborated conclusions by means of the measuring card.
|
|
|
Numerical image processing methods for rotating condenser microscope images processing
Týč, Matěj ; Martišek, Dalibor (referee) ; Druckmüller, Miloslav (advisor)
Tato práce popisuje vznik obrazu v transmisním světelném mikroskopu s proměnnou aperturou kondenzoru. Tento způsob pořizování obrazu je výhodný při pozorování tlustých vzorků, což jsou objekty, u kterých je v mikroskopickém měřítku významná výška. Klasické transmisní mikroskopy pro tento výzkum vhodné nejsou, protože výsledný obraz, který produkují, obsahuje patrné informace z velkého objemu vzorku mimo oblast, která je vyšetřovaná. Tento problém byl vyřešen po vynálezu konfokálního mikroskopu, který je ovšem daleko dražší a má i některé nevýhody navíc. Cílem je zpracovat obrazy pořízené pomocí kondenzoru s rotující aperturou tak, aby došlo k redukci podílu nežádoucí informace a obraz se tak stal "čistším". Tato metoda zpracování obrazu nemohla být použita v minulosti, protože tehdejší počítače neměly dostatečnou paměť a výkon. Na tuto metodu se dá nahlížet jako na převod množiny výstupů z mikroskopu s vylepšenou osvětlovací soustavou na odpovídající množinu výstupů konfokálního mikroskopu.
|
|
|
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.
|
guest ::
