|
| |
|
|
Image similarity measuring using deep learning
Štarha, Dominik ; Šeda, Pavel (referee) ; Rajnoha, Martin (advisor)
This master´s thesis deals with the reseach of technologies using deep learning method, being able to use when processing image data. Specific focus of the work is to evaluate the suitability and effectiveness of deep learning when comparing two image input data. The first – theoretical – part consists of the introduction to neural networks and deep learning. Also, it contains a description of available methods, their benefits and principles, used for processing image data. The second - practical - part of the thesis contains a proposal a appropriate model of Siamese networks to solve the problem of comparing two input image data and evaluating their similarity. The output of this work is an evaluation of several possible model configurations and highlighting the best-performing model parameters.
|
|
|
Interactive software tools for teaching signal and image processing
Had, Pavel ; Rajmic, Pavel (referee) ; Mangová, Marie (advisor)
This thesis deals with the development of interactive applets for educational purposes. There are four applets: linear image combinations, least squares method and linear regression, discrete linear convolution in 2D, and interpolation in 1D. Each part of this thesis consists of a theoretical analysis of a given problem and its implementation in JavaScript. Specific applets then illustrate the problem so that it can be easily understood.
|
|
|
Parallel Programming in Rust Language
Šlampa, Ondřej ; Bařina, David (referee) ; Kobrtek, Jozef (advisor)
Topic of this thesis is parallelization in Rust. Aim of this thesis is to compare performance and usability of Rust language with already used alternative - OpenMP. Computation of n-dimensional comvolution was used for benchmark. In conclusion there is evaluation of results and suggestions for their future use.
|
|
|
Image based smoke and fire detection
Ďuriš, Denis ; Burda, Karel (referee) ; Přinosil, Jiří (advisor)
This diploma thesis deals with the detection of fire and smoke from the image signal. The approach of this work uses a combination of convolutional and recurrent neural network. Machine learning models created in this work contain inception modules and blocks of long short-term memory. The research part describes selected models of machine learning used in solving the problem of fire detection in static and dynamic image data. As part of the solution, a data set containing videos and still images used to train the designed neural networks was created. The results of this approach are evaluated in conclusion.
|
|
|
Deep Learning for Facial Recognition in Video
Mihalčin, Tomáš ; Sochor, Jakub (referee) ; Hradiš, Michal (advisor)
This diploma thesis focuses on a face recognition from a video, specifically how to aggregate feature vectors into a single discriminatory vector also called a template. It examines the issue of the extremely angled faces with respect to the accuracy of the verification. Also compares the relationship between templates made from vectors extracted from video frames and vectors from photos. Suggested hypothesis is tested by two deep convolutional neural networks, namely the well-known VGG-16 network model and a model called Fingera provided by company Innovatrics. Several experiments were carried out in the course of the work and the results of which confirm the success of proposed technique. As an accuracy metric was chosen the ROC curve. For work with neural networks was used framework Caffe.
|
|
|
Interactive software tools for teaching signal processing
Pacas, Ondrej ; Rajmic, Pavel (referee) ; Mangová, Marie (advisor)
This thesis deals with creation of four interactive applications for educational purposes in the field of digital signal processing. The goal of this work is to create four applications which will visually interpretate each of the methods of signal processing. This involves applications for linear regression and least squares method, interpolation and signal reconstruction from its samples, discrete linear convolution and discrete cross-correlation. Applications are created using JavaScript programming language.
|
|
|
Implementation of edge detector using wavelet transform
Pálka, Zbyněk ; Rášo, Ondřej (referee) ; Růčka, Lukáš (advisor)
This thesis is focused on edge detection in image. In theoretical part are contained genarally used methods of edge detection using first and second-order derivate and both of mentioned methods are described here. Further it’s deiscribed here continuous, descrete and two dimensional descrete wavelet transform and process of noise removing in image by descrete wavelet transform. In next part are analysed two methods of edge detection using wavelet transform and their possible realizations in program Matlab. In practical part of thesis is in detail described algorithm of program on edge detection using wavelet transform and it‘s described here individual functions of program. The main content of practical part are visual results of wavelet edge detector and their comparison with Canny, Prewitt and Sobel edge detector.
|
|
| |
|
|
Descriptor for Identification of a Person by the Face
Coufal, Tomáš ; Orság, Filip (referee) ; Goldmann, Tomáš (advisor)
Thesis provides an overview and discussion of current findings in the field of biometrics. In particular, it focuses on facial recognition subject. Special attention is payed to convolutional neural networks and capsule networks. Thesis then lists current approaches and state-of-the-art implementations. Based on these findings it provides insight into engineering a very own solution based of CapsNet architecture. Moreover, thesis discussed advantages and capabilitied of capsule neural networks for identification of a person by its face.
|
guest ::
