The processing of medical image information in the context of this thesis means a complex of activities that can be achieved using ICT, needed to ensure effective acquisition, primary diagnosis, remote consultation, reliable archiving and other specific activities. The thesis describes the possibility of utilization of ICT in this environment, related trends and activities in the Czech Republic and in the world as well as a number of limitations, which result mainly from the applicable legislation. The main idea of this thesis is the integration platform proposal that represents a new alternative to the integration of existing services and DICOM applications in this field. Platform provides an environment for new interesting applications and enables the medical image processing to be organised different way. The system of efficient redistribution of requirements for the processing of medical image information within the coalition of cooperating medical institutions is describes as an application based on this platform. Increasing the efficiency of processing is achieved through greater specialization, more efficient diagnosis associated with access to the latest knowledge and efficient use of expensive equipment capacity and time of medical specialists. Part of this thesis is the methodology of implementation of this integration platform into medical institutions, placing particular emphasis on the risks associated with this way of integration.

This work aims at content-based image search. Different approaches to this type of search are investigated. The main focus of the thesis is special category of content-based image search called sketch-based image search. The most important descriptor types used for image feature extraction in image search are analyzed. Main contribution of the thesis to this research area is a new feature extraction method based on sketch-based image search. This method is implemented together with search interface. The method was evaluated by three test persons. The testing results show promising properties of new method and suggest further possible improve-ments. Powered by TCPDF (www.tcpdf.org)

DISSERTATION ABSTRACT JUDr. Milan Chládek Camera systems and video records in legal protection of privacy The main goal of this dissertation named Camera systems and video records in legal protection of privacy is the basic analysis and familiarization with the highest actual and in the recent time wide-discussed problems. The field of the video surveillance is highly interesting and for the time being by the law science not solved topic. The legal science and practice solve problem belongs to this problematic area often as you go along, often by the aplication of the more generic rules and therefore the deciding authorities often make the law complete by theirselves because the legislator was not able to cover all the possible situations - just because of high actuality and novelty of this topic. This work tries to cover the topis by the relative wide way, from the generic introduction and tematic survey of the right to privacy offers first the concrete work with generic topic of right to privacy in relation to the video records, further focusing on camera systems and the last third of the work focuses on highly modern technologies of using video surveillance and on other methods using video records and snapshots in the area of informatic technologies and further areas of the use. The dissertation is...

In accordance with the latest researches this Diploma Thesis is not only focused on the general development of individual collections but deals with investigation of individual aspects of a particular example. The picture collection that was used for this purpose can be found within the yard of Humprecht Jan Černín from Chudenice and dates from the second half of the 17th century. Primarily, the Diploma Thesis strives to get hold of those aspects that influenced the relation of Humprecht Jan Černín to fine art, mainly in term of economic and social background including his personality traits. It concentrates on such events that awakened his interest in fine arts, for example education, effort to improve and consolidate his social position or effort to continue in the tradition of his ancestors.

No description available.

Image filters is a subset of signal processing. Image filtering is mainly used for highlighting an information. It can be useful for reduce noise, smooth pictures, enhance contrast or for edge detection. Image filter design itself is a time-consuming process. It is suitable to automate the process and give up the function of filter designing to preprogrammed system. Designing komponents for that system is aim of this work. It is part of an whole expert system. A set of information is given on input which are used for generating new image filters. Subsequently it will evaluate the relevancy of concrete image filter for subsequent use.

This document describes implementation of photo slideshow editor. This editor can be used to create dynamic sequences from taken photos. Image taken by camera is projected onto three-dimensional sphere and drawn to screen. Then it is posible to rotate and zoom camera over image. Visual output of this editor makes moving over image more real. If panoramic image is used, user is able to free look around. This document describes method which can translate two-dimensional coordinates to three-dimensional space. Shows how to use transformations for moving camera and methods to implement camera zoom. Contains description of user interface and also mentions extensions that were implemented in editor.

An AdaBoost algorithm for construction of strong classifier from several weak hypotesis will be presented in this work. Theoretical background of the algorithm and the method of construction of strong classifiers will be explained. WaldBoost extension to the algorithm will be described. The thesis deals with image features that are often used as element of weak classifiers. Brief introduction to pattern recognition in context of computer vision will be outlined in the begining of the work. Also some widely used methods of classifier training will be presented. An object detection library based on AdaBoost classifiers was developed as part of the work. The library was used in implementation of software that in praktice demonstrates object detection in videosquences. Last part of the work describes tool for training of AdaBoost classifiers.

The thesis deals with the issue of linking visual representation of a literary work of art, especially with the connection of Karel Teige typographical book envelopes to the poetry collections of Czech authors of the first half of the twentieth century. It focuses on the period of Czech avant-garde and new possibilities and limits of genre, artistic and semiotic definition. Attention is also devoted to contemporary anthology, professional journals and articles, especially by Karel Teig's production, in which he illustrates his concept of modern art. It also includes the marketing and aesthetic-educational character of visual imagery in literature for children and youth.

This thesis deals with the polymorphic image filter design. The study includes polymorphic circuits, their theoretical base and practical applications. It further focuses on the cartesian genetic programming that can be used for an evolutionary design of some types of image filters. The thesis continues with the specification of the evolutionary algorithm to be used for the design of the polymorphic image filters. The implementation of the algorithm is described in two versions -- a standard one running only on a CPU and an accelerated one that partially uses the GPU. Several polymorphic image filters are designed by means of the algorithm.