|
|
Face superresolution from image sequence
Mezina, Anzhelika ; Rajnoha, Martin (referee) ; Burget, Radim (advisor)
Táto práce se zabývá použitím hlubokého učení neuronových sítí ke zvýšení rozlišení obrázků, které obsahují obličeje. Tato metoda najde uplatnění v různých oblastech, zejména v bezpečnosti, například, při bezpečnostním incidentu, kdy policie potřebuje identifikovat podezřelého z nahraného videa ze sledovací kamery. Cílem této práce je navrhnout minimálně dvě architektury neuronových sítí, které budou pracovat se sekvencí snímků, a porovnat je s metodami zpracování jediného snímku. Pro tento účel je také vytvořena nová trénovací množina, obsahující sekvenci snímku obličeje. Metody zpracování jednoho snímku jsou natrénované na nové množině. Dále jsou navrženy nové metody zvětšení obrázků na základě sekvence snímků. Tyto metody jsou založené na U-Net modelu, který je úspěšný v segmentaci, ale také v superrozlišení. Pro zlepšení architektury byly použity reziduální bloky a jejich modifikace, a navíc také percepční ztrátová funkce, která dovoluje vyhnout se rozmazání a získání více detailů. První čast této práce je věnovana popisu neuronových sítí a některých architektur, jejichž modifikace mohou být použity v superrozlišení. Druhá část se poté zabývá popisem metod pro zvýšení rozlišení obrazu pomocí jednoho snímku, několika snímků a videa. Ve třetí části jsou popsány navržené metody a experimenty a v poslední části porovnaná metod založených na jednom snímku a několika snímcích. Navržené metody jsou schopny získat více detailů v obraze, ale mohou produkovat artefakty. Ty lze ale poté eliminovat pomocí filtru, například Gaussova. Nové metody méně selhávají při detekci obličejů, a to je podstatné u identifikace člověka v případě incidentu.
|
|
|
Dataset generation for specific cases of face recognition
Kolmačka, Tomáš ; Kolařík, Martin (referee) ; Rajnoha, Martin (advisor)
The diploma thesis deals with current problems of person identification and deep learning. Furthermore, the work deals mainly with obtaining quality and diverse data that are used to train deep learning with convolutional neural networks for face recognition. There is very little public access to such data, so the practical part focuses on creating the MakeHuman plugin that will generate a database of random face images. It is possible to generate faces according to five different scenarios in which purely random faces or faces where the same can be seen with modifications such as different hair, beard, hat, glasses and more are created. The scenarios also allow you to generate faces with some expressions or faces as they age. You can set some parameters that give the appearance of the resulting database in the plugin. This can include face images from different angles of rotation, zooming and lighting.
|
|
|
Determination of Objects Similarity Based on Image Information
Rajnoha, Martin ; Kamencay,, Patrik (referee) ; Beneš, Radek (referee) ; Burget, Radim (advisor)
Monitoring of public areas and their automatic real-time processing became increasingly significant due to the changing security situation in the world. However, the problem is an analysis of low-quality records, where even the state-of-the-art methods fail in some cases. This work investigates an important area of image similarity – biometric identification based on face image. The work deals primarily with the face super-resolution from a sequence of low-resolution images and it compares this approach to the single-frame methods, that are still considered as the most accurate. A new dataset was created for this purpose, which is directly designed for the multi-frame face super-resolution methods from the low-resolution input sequence, and it is of comparable size with the leading world datasets. The results were evaluated by both a survey of human perception and defined objective metrics. A hypothesis that multi-frame methods achieve better results than single-frame methods was proved by a comparison of both methods. Architectures, source code and the dataset were released. That caused a creation of the basis for future research in this field.
|
|
|
Machine Understanding for Text Messages Used in Aviation
Lieskovský, Pavol ; Rajnoha, Martin (referee) ; Povoda, Lukáš (advisor)
This work deals with problems of NOTAM in text format, which is used in aeronautics. It documents the difference between text and digital format of NOTAM, special types of NOTAM messages and items from which the NOTAM consist of. It describes syntax and the functions of program, which was made within the frame of this thesis. The program is fully capable of correct parsing and processing of the NOTAM. The program can display each area of processed NOTAM messages in map and also provides detection of collision between these areas and flight plan
|
|
|
Warehouse modeling using graphical user interface
Rajnoha, Martin ; Mašek, Jan (referee) ; Burget, Radim (advisor)
Master’s thesis proposes a new algorithm which enables efficient conversion of graphical representation of warehouse into graph theory representation and consequently accelerates estimation for route costs. The proposed algorithm computes route distances between any places in warehouse based on Breadth first search, image processing „skeletonization“ and Dijkstra algorithm. Using the proposed algorithm it is possible to search routes in a warehouse effectively and fast using precomputed routing table. Searching time is less then milisecond using routing table and even size of warehouse doesn’t affect it significantly instead of using Dijkstra algorithm.
|
|
|
Prototype Verification of Modification of Evolutionary Algorithm
Švestka, Marek ; Rajnoha, Martin (referee) ; Šeda, Pavel (advisor)
This thesis is about evolutionary algorithms with a concrete solution for an Aircraft Landing Problem. The goal is to create a genetic algorithm for this task resolution, apply selected modifications and compare all outputs. The program runs with different selection methods which are further reviewed. Input data are taken from Operations research library for this task. The outcome of this thesis gives a closer look to evolutionary programming and it’s problem resolution.
|
|
|
Extreme learning machines for time series prediction
Zmeškal, Jiří ; Rajnoha, Martin (referee) ; Burget, Radim (advisor)
Thesis is aimed at the possibility of utilization of extreme learning machines and echo state networks for time series forecasting with possibility of utilizing GPU acceleration. Such predictions are part of nearly everyone’s daily lives through utilization in weather forecasting, prediction of regular and stock market, power consumption predictions and many more. Thesis is meant to familiarize reader firstly with theoretical basis of extreme learning machines and echo state networks, taking advantage of randomly generating majority of neural networks parameters and avoiding iterative processes. Secondly thesis demonstrates use of programing tools, such as ND4J and CUDA toolkit, to create very own programs. Finally, prediction capability and convenience of GPU acceleration is tested.
|
|
|
Analysis of the communication path attributes for IP geolocation
Rajnoha, Martin ; Komosný, Dan (referee) ; Balej, Jiří (advisor)
The aim of this thesis was to study current resources to find location of stations in the network Internet, mainly active methods that are based on delay measurements. Describe origin of the delay and its parts. Next create an application that is able remotely measure the delay between stations and convert this delay to distance. Aplication calculate geographic position of station on based this distances. For measurement was used experimental network PlanetLab.
|
|
|
The effect of the background and dataset size on training of neural networks for image classification
Mikulec, Vojtěch ; Kolařík, Martin (referee) ; Rajnoha, Martin (advisor)
This bachelor thesis deals with the impact of background and database size on training of neural networks for image classification. The work describes techniques of image processing using convolutional neural networks and the influence of background (noise) and database size on training. The work proposes methods which can be used to achieve faster and more accurate training process of convolutional neural networks. A binary classification of Labeled Faces in the Wild dataset is selected where the background is modified with color change or cropping for each experiment. The size of dataset is crucial for training convolutional neural networks, there are experiments with the size of training set in this work, which simulate a real problem with the lack of data when training convolutional neural networks for image classification.
|
|
|
Handwritten text recognition using a sliding window
Ďuriš, Denis ; Povoda, Lukáš (referee) ; Rajnoha, Martin (advisor)
This bachelor thesis deals with optical character recognition. It focuses on recognizing hand-written text. The theoretical introduction describes the methods used for optical character recognition and selected machine learning methods. Subsequently, the work describes two methods for making cutouts of characters, using a sliding window. Cutouts are used in training and testing datasets of machine learning models. The document includes methods to improve the accuracy of character recognition. The accuracy of the models is evaluated in conclusion. Charcters in cutouts are clasified by an automated recognition program.
|
guest ::
RSS feed.