The objective of this thesis is to implement a web application designed for recommendation of stock photos. The application gets the input from newspaper articles in Czech or English and, based on the text itself, suggests appropriate stock photos. The implemented application also searches images according to visual similarity. The thesis deals with theoretical aspects of keywords extraction and language of text detection. Further it analyzes possibilities of efficient search for similar vectors that are used in the search component for visually similar images. It also describes the possibilities in development of modern web frontend and backend. The quality of algorithm for recommending stock photos is tested on users. Powered by TCPDF (www.tcpdf.org)

We build a joint multimodal model of text and images for automatically assigning illustrative images to journalistic articles. We approach the task as an unsupervised representation learning problem of finding a common representation that abstracts from individual modalities, inspired by multimodal Deep Boltzmann Machine of Srivastava and Salakhutdinov. We use state-of-the-art image content classification features obtained from the Convolutional Neural Network of Krizhevsky et al. as input "images" and entire documents instead of keywords as input texts. A deep learning and experiment management library Safire has been developed. We have not been able to create a successful retrieval system because of difficulties with training neural networks on the very sparse word observation. However, we have gained substantial understanding of the nature of these difficulties and thus are confident that we will be able to improve in future work.

This work has aimed to implement an easy-to-use application which can be used to navigate through aerial imagery, assign sections of this image for different classes. Based on these category assignments the application can autonomously assign categories to so-far unknown fields, hence it helps the user in further classification. The output of the application is an index file, which can serve as underlying dataset for further analysis of a given area from geographic or economic point-of-view. To fulfil this task the program uses standard MPEG-7 descriptors to perform the feature extraction upon which the classification relies.

Táto práca sa zaoberá určením neistoty v predikciách modelov hlbokého učenia. Aj keď sa týmto modelom darí dosahovať vynikajúce výsledky v mnohých oblastiach počítačového videnia, ich výstupy sú väčšinou deterministické a neposkytujú mnoho informácií o tom, ako si je model istý svojou predpoveďou. To je obzvlášť dôležité pri analýze lekárskych obrazových dát, kde môžu mať omyly vysokú cenu a schopnosť detekovať neisté predikcie by umožnila dohliadajúcemu lekárovi spracovať relevantné prípady manuálne. V tejto práci aplikujem niekoľko rôznych metrík vyvinutých v nedávnom výskume pre určenie neistoty na modely hlbokého učenia natrénované pre lokalizáciu cefalometrických landmarkov. Následne ich vyhodnotím a porovnávam v sade experimentov, ktorých úlohou je určiť, nakoľko jednotlivé metriky poskytujú užitočnú informáciu o tom, ako si je model istý svojou predpoveďou.

This master's thesis deals with acceleration of pixel interpolation methods using the GPU and NVIDIA (R) CUDA TM architecture. Graphic output is represented by a demonstrational application for geometrical image transforms using chosen interpolation method. Time critical parts of the code are moved on the GPU and executed in parallel. There are used highly optimized routines from the OpenCV library, made by the Intel company for an image and video processing.

Resume The thesis is focused mainly on the rights of phonogram and audiovisual fixation producers. Choosing this topic came as a result of my own personal interest in music, as well as the constantly active public debate regarding the protection of rights of the producers in relation to the expantion of internet and related transmission of digital data. Part one is followed by establishing main terms, specifically the phonograms and their producers, and audiovisual fixations and their producers. The history of copyright protection and related rights is discussed in the third part. Despite the long history of intelectual property protection, copyright and related rights were not included into the Czech legal system until 1953. The historical excursion into copyright and related rights leads to exploration of the rights of phonograms and audiovisual fixations producers, especially in the light of how easy their worldwide distribution in today`s world is. Copyright is based on the quasidual concept of personal and property rights. Producers of phonograms or audiovisual fixations are granted solely property rights. The last two chapters are devoted to the explanation of individual rights and their potential civil or public protection under the valid Czech legal system.

This thesis focuses on advanced methods of detecting contours of the cardiac cells and measuring their contraction. The theoretical section describes the types of confocal microscopes, which are used for capturing biological samples. The following chapter is devoted to the methods of cardiac cells segmentation, where we are introduced to the generally applied approaches. The most widely spread methods of segmentation are active contours and mathematical morphology, which are the crucial topics of this thesis. Thanks to the those methods we are able in the visual data to accurately detect required elements and measure their surface chnage in time. Acquired theoretical knowledge leads us to the practical realization of the methods in MATLAB.

Ongoing expansion of digital images requires new methods for sorting, browsing, and sear- ching through huge image databases. This is a domain of Content-Based Image Retrieval (CBIR) systems, which are database search engines for images. A user typically submit a query image or series of images and the CBIR system tries to find and to retrieve the most similar images from the database. Optimally, the retrieved images should not be sensitive to circumstances during their acquisition. Unfortunately, the appearance of natural objects and materials is highly illumination and viewpoint dependent. This work focuses on representation and retrieval of homogeneous images, called textu- res, under the circumstances with variable illumination and texture rotation. We propose a novel illumination invariant textural features based on Markovian modelling of spatial tex- ture relations. The texture is modelled by Causal Autoregressive Random field (CAR) or Gaussian Markov Random Field (GMRF) models, which allow a very efficient estimation of its parameters, without the demanding Monte Carlo minimisation. Subsequently, the estimated model parameters are transformed into the new illumination invariants, which represent the texture. We derived that our textural representation is invariant to changes of illumination intensity and...

The thesis is concerned with optical character recognition from image data with different methods used for character classification. In the first theoretical part it focuses on explanation of all important parts of system for optical character recognition. The latter practical part of the thesis describes an example of image segmentation, the implementation of artificial neural networks for image recognition and create simple training set of data for the evaluation of the network. It also describes the process of training Tesseract tool and its implementation in a simple application EasyTessOCR for character recognition.