|
|
Deep Neural Networks Approximation
Stodůlka, Martin ; Mrázek, Vojtěch (referee) ; Vaverka, Filip (advisor)
The goal of this work is to find out the impact of approximated computing on accuracy of deep neural network, specifically neural networks for image classification. A version of framework Caffe called Ristretto-caffe was chosen for neural network implementation, which was extended for the use of approximated operations. Approximated computing was used for multiplication in forward pass for convolution. Approximated components from Evoapproxlib were chosen for this work.
|
|
|
Optical Character Recognition Using Convolutional Networks
Csóka, Pavel ; Behúň, Kamil (referee) ; Hradiš, Michal (advisor)
This thesis aims at creation of new datasets for text recognition machine learning tasks and experiments with convolutional neural networks on these datasets. It describes architecture of convolutional nets, difficulties of recognizing text from photographs and contemporary works using these networks. Next, creation of annotation, using Tesseract OCR, for dataset comprised from photos of document pages, taken by mobile phones, named Mobile Page Photos. From this dataset two additional are created by cropping characters out of its photos formatted as Street View House Numbers dataset. Dataset Mobile Nice Page Photos Characters contains readable characters and Mobile Page Photos Characters adds hardly readable and unreadable ones. Three models of convolutional nets are created and used for text recognition experiments on these datasets, which are also used for estimation of annotation error.
|
|
|
Detection and Classification of Road Users in Aerial Imagery Based on Deep Neural Networks
Hlavoň, David ; Hradiš, Michal (referee) ; Rozman, Jaroslav (advisor)
This master's thesis deals with a vehicle detector based on the convolutional neural network and scene captured by drone. Dataset is described at the beginning, because the main aim of this thesis is to create practicly usable detector. Architectures of the forward neural networks which detector was created from are described in the next chapter. Techniques for building a detector based on the naive methods and current the most successful meta architectures follow the neural network architectures. An implementation of the detector is described in the second part of this thesis. The final detector was built on meta architecture Faster R-CNN and PVA neural network on which the detector achieved score over 90 % and 45 full HD frames per seconds.
|
|
| |
|
|
Semantic segmentation of images using convolutional neural networks
Špila, Filip ; Věchet, Stanislav (referee) ; Krejsa, Jiří (advisor)
Tato práce se zabývá rešerší a implementací vybraných architektur konvolučních neuronových sítí pro segmentaci obrazu. V první části jsou shrnuty základní pojmy z teorie neuronových sítí. Tato část také představuje silné stránky konvolučních sítí v oblasti rozpoznávání obrazových dat. Teoretická část je uzavřena rešerší zaměřenou na konkrétní architekturu používanou na segmentaci scén. Implementace této architektury a jejích variant v Caffe je převzata a upravena pro konkrétní použití v praktické části práce. Nedílnou součástí tohoto procesu jsou kroky potřebné ke správnému nastavení softwarového a hardwarového prostředí. Příslušná kapitola proto poskytuje přesný návod, který ocení zejména noví uživatelé Linuxu. Pro trénování všech variant vybrané sítě je vytvořen vlastní dataset obsahující 2600 obrázků. Je také provedeno několik nastavení původní implementace, zvláště pro účely použití předtrénovaných parametrů. Trénování zahrnuje výběr hyperparametrů, jakými jsou například typ optimalizačního algoritmu a rychlost učení. Na závěr je provedeno vyhodnocení výkonu a výpočtové náročnosti všech natrénovaných sítí na testovacím datasetu.
|
|
|
Captcha Code Recognition
Pazderka, Radek ; Rozman, Jaroslav (referee) ; Zbořil, František (advisor)
This bachelor thesis is dedicated to design and implementation of application , which's purpose is to recognize text CAPTCHA codes . It describes image processing algorithms , segmentation algorithms and character classification . Two different aproaches were used for classification . Convolution neural network LeNet and histogram classificator , which uses Pearson's correlation coefficient . Chosen classificators were tested on different CAPTCHA codes while finding out the success rate of recognition .
|
|
|
Semantic Segmentation in Mountainous Environment
Pelikán, Jakub ; Čadík, Martin (referee) ; Brejcha, Jan (advisor)
Semantic segmentation is one of classic computer vision problems and strong tool for machine processing and understanding of the scene. In this thesis we use semantic segmentation in mountainous environment. The main motivation of this work is to use semantic segmentation for automatic location of geographic position, where the picture was taken. In this thesis we evaluated actual methods of semantic segmentation and we chose three of them that are appropriate for adapting to mountainous environment. We split the dataset with mountainous environment into validation, train and test sets to use for training of chosen semantic segmentation methods. We trained models from chosen methods on mountainous data. We let segments from the best trained models get evaluated in electronic survey by respondents and we evaluated these segments in process of camera orientation estimation. We showed that chosen methods of semantic segmentation are possible to use in mountainous environment. Our models are trained on 11, 5 or 4 mountainous classes and the best of them achieve on 4 class mean IU 57.4%. Models are usable in practise. We show it by their deployment as a part of camera orientation estimation process.
|
|
|
Depth Estimation by Convolutional Neural Networks
Ivanecký, Ján ; Španěl, Michal (referee) ; Hradiš, Michal (advisor)
This thesis deals with depth estimation using convolutional neural networks. I propose a three-part model as a solution to this problem. The model contains a global context network which estimates coarse depth structure of the scene, a gradient network which estimates depth gradients and a refining network which utilizes the outputs of previous two networks to produce the final depth map. Additionally, I present a normalized loss function for training neural networks. Applying normalized loss function results in better estimates of the scene's relative depth structure, however it results in a loss of information about the absolute scale of the scene.
|
|
|
Convolution neural networks on the Windows platform
Kapusta, Martin ; Rajnoha, Martin (referee) ; Přinosil, Jiří (advisor)
The aim of the bachelor thesis is the latest knowledge of convolution neural networks and their application. The thesis describes the history, biological neuron and analogous mathematical model of a neuron. It also deals with the areas where neural networks are used, as well as the areas in which they expand gradually, the ways of learning and training, the differences between convolution neural networks and classical neural networks and their architecture. The thesis consists of two parts. The first part is the selection of the framework for working with convolution neural networks, which is suitable for implementation in the Windows operating system, the installation of the framework and its troubleshooting. The second part is aimed at creating an automated installation tool for the Windows 7 and Windows 10 operating system, created in JavaFX.
|
|
|
Detection of Fire in Video
Poledník, Tomáš ; Hradiš, Michal (referee) ; Herout, Adam (advisor)
{This thesis deals with fire detection in video by colour analysis and machine learning, specifically deep convolutional neural networks, using Caffe framework. The aim is to create a vast set of data that could be used as the base element of machine learning detection and create a detector usable in real application. For the purposes of the project a set of tools for fire sequences creation, their segmentation and automatic labeling is proposed and created together with a large test set of short sequences with artificial modelled fire.
|
guest ::
