There are billions of photos on the internet and as the size of these digital repositories grows, finding target picture becomes more and more difficult. To increase the informational quality of photo albums we propose a new method that selects representative pictures from a group of photographs using computer vision algorithms. The aim of this study is to analyze the issues about image features, image similarity, object clustering and examine the specific characteristics of photographs. Tests show that there is no universal image descriptor that can easily simulate the process of clustering performed by human vision. The thesis proposes a hybrid algorithm that combines the advantages of selected features together using a specialized multiple-step clustering algorithm. The key idea of the process is that the frequently photographed objects are more likely to be representative. Thus, with a random selection from the largest photo clusters certain representative photos are obtained. This selection is further enhanced on the basis of optimization, where photos with better photographic properties are being preferred.

The diploma thesis is devided into two parts - the theoretical and the practical one. The theoretical part deal with contemporary issues of aphasia in the context of various scientifics discipline and aphasia access. I analyze aphasia classifications, diagnostics, therapy and using of the aids in aphasia therapy. The practical part describes my work - project and realisation of reeducational aid for people with aphasia, which name is Soubor sekvencí dějových obrázků. I devote to detailed describtion of this aid in the final chapter. The aim of the diploma thesis was to widen offer reeducational materiál for people with aphasia in our conditions. Powered by TCPDF (www.tcpdf.org)

04.01.17 abstract.txt 1 file:///home/misa/Desktop/dp/abstract.txt The primary purpose of this thesis is to determine criteria for a high- dynamic range (HDR) image viewer accented by computer graphics artists and other users who work with HDR images produced by physically-based renderers on a daily basis. Also an overview of already existing solutions is present. Based on both of them, a new HDR viewer is designed and implemented giving an emphasis on its memory and performance efficiency. For these purposes two alternative image data layouts, Array-of-Structures (AoS) and Structure-of-Arrays (SoA), are discussed and their impact is measured on the speed of an algorithm for changing image saturation which has been selected as a representative part of whole tone mapping process of the viewer. It has turned out that the latter type of layout allows the algorithm to run about 3 times faster or more under the conditions of a defined testing environment. The thesis has two main contributions. First it gives the above users a tool which could help them when working with HDR images. Second it indicates that there may be a potential of significant speed-up of implementations of tone mapping algorithms.

Grayscale pictures were never replaced by color ones and will probably never be, because they are indispensable in many areas. In this thesis was chosen three methods for color-to-gray conversion. These methods was implemented afterwards. Within this thesis was also made test set of 24 HDR pictures, which was together with existing set of 24 LDR pictures used to test and evaluate features of implemented methods. These methods were also compared from the point of accurancy and preference using questionnaire.

The thesis deals with the detection and classification of flying objects. The work can be divided into three parts. The first part describes the creation of dataset of flying objects. The reverse image search is used to create the dataset. The next part is a research of algorithms for detection, tracking and classification. Subsequently, the individual algorithms are applied and evaluated. In the last part, the design of hardware components is performed.

Eyewitness identification plays an important role during criminal proceedings and may lead to prosecution and conviction of a suspect. One of the methods of eyewitness identification is a police photo lineup when a collection of photographs is presented to the witness in order to identify the perpetrator of the crime. In the lineup, there is typically at most one photograph (typically exactly one) of the suspect and the remaining photographs are the so-called fillers, i.e. photographs of innocent people. Positive identification of the suspect by the witness may result in charge or conviction of the suspect. Assembly of the lineup is a challenging and tedious problem, because the wrong selection of the fillers may end up in a biased lineup, where the suspect will stand out from the fillers and would be easily identifiable even by a highly uncertain witness. The reason why it is tedious is due to the fact that this process is still done manually or only semi-automatically. This thesis tries to solve both issues by proposing a model that will be capable of generating synthetic data, together with an application that will allow users to obtain the fillers for a given suspect's photograph. 1

Tato práce se zabývá automatickým generovaním popisů obrázků s využitím několika druhů neuronových sítí. Práce je založena na článcích z MS COCO Captioning Challenge 2015 a znakových jazykových modelech, popularizovaných A. Karpathym. Navržený model je kombinací konvoluční a rekurentní neuronové sítě s architekturou kodér--dekodér. Vektor reprezentující zakódovaný obrázek je předáván jazykovému modelu jako hodnoty paměti LSTM vrstev v síti. Práce zkoumá, na jaké úrovni je model s takto jednoduchou architekturou schopen popisovat obrázky a jak si stojí v porovnání s ostatními současnými modely. Jedním ze závěrů práce je, že navržená architektura není dostatečná pro jakýkoli popis obrázků.

In a known-item search task (KIS), the goal is to find a previously seen image in a multimedia collection. In this thesis, we discuss two different approaches based on the visual description of the image. In the first one, the user creates a collage of images (using images from an external search engine), based on which we provide the most similar results from the dataset. Our results show that preprocessing the images in the dataset by splitting them into several parts is a better way to work with the spatial information contained in the user input. We compared the approach to a baseline, which does not utilize this spatial information and an approach that alters a layer in a deep neural network. We also present an alternative approach to the KIS task, search by faces. In this approach, we work with the faces extracted from the images. We investigate face representation for the ability to sort the faces based on their similarity. Then we present a structure that allows easy exploration of the set of faces. We provide a demo, implementing all presented techniques.

This work focuses on a possibility of using current computer vision alghoritms and methods for automatic similarity matching of so called graffiti tags. Those are such graffiti, that are used as a fast and simple signature of their authors. The process of development and implementation of CBIR system, which is created for this task, is described. For the purposes of finding images similarity, local features are used, most notably self-similarity features.

The thesis covers sociolinguistic and psycholinguistic aspects of Czech and Slovak language relations. To both fields, it contributes in the form of own empirical research. At the centre of attention are native speakers of Slovak living long-term in Czechia and their language behaviour under this setting in relation to Czech and Slovak. Given that two languages in question are genetically very close and mutual intelligible, the actual language behaviour of the described population is not strictly predetermined by the social norms (Dickins, 2009). However, there are also conditions supporting the accommodation to Czech (Sloboda, 2005). The thesis focuses on the identification of factors influencing language choice and on the impacts of such factors on the psychlinguistic processing of Slovak and Czech words. The sociolinguistic part builds on questionnaire-based surveys, such as those conducted by Sloboda (2006). The own questionnaire survey was carried out via web. The data from 651 respondents were assessed, all from native speakers of Slovak having grown up in Slovakia and commencing their stay in Czechia after the age of 18. The data revealed that Slovak is used more than Czech, that Czech is more often perceived, that the use of Czech is more common in the communication with strangers or in...