|
|
Photographic Detail Enhancement Methods
Sedlář, Pavel ; Zemčík, Pavel (referee) ; Čadík, Martin (advisor)
The aim of this Bachelor Thesis, which falls within the field of computer vision, is to get acquainted with the issue of methods that can highlight detail in the image. This work also describes specific methods that will later be implemented and with which, last but not least, experiment for further use.
|
|
|
Video Enhancement Using Convolutional Networks
Skácel, David ; Špaňhel, Jakub (referee) ; Hradiš, Michal (advisor)
Convolutional neural networks (CNN) represent a state-of-the-art approach to non-trivial image processing tasks, including compression artifacts reduction and image super-resolution. As some research groups nowadays show, these networks can also be leveraged to perform such tasks on real-world video data, resulting in video spatial super-resolution and more. The main goal of this work is to determine whether these nets can be adjusted to perform temporal super-resolution of real-world video data. I utilize the aforementioned neural net architectures in this paper to do so. As I show, given that the input videos are of reasonable quality, these nets are capable of double-image interpolation up to a certain level, where the output image is usable for temporal upsampling. Although the presented results are promising, I encourage more research to be done on this topic.
|
|
|
Study of potential of heat transfer enhancement in process plant
Němeček, Zbyněk ; Kilkovský, Bohuslav (referee) ; Jegla, Zdeněk (advisor)
This diploma thesis is a study of the potential of heat transfer enhancement in the process of hydrogenation refining of oil. The simulation of the process and the heat-hydraulic analysis of the heat exchanger network are performed using the software tools. Based on the obtained results and the results of the optimization study, a new heat exchanger is placed in the process and its parameters are subject to further calculations. The aim is to study the possibilities of heat transfer enhancement for the newly used heat exchanger and to discuss aspects connected with the use of selected software.
|
|
|
Removal of the masonry pillar in the front wall of the apartment house
Vítková, Barbora ; Bažant,, Zdeněk (referee) ; Strnad, Jiří (advisor)
This thesis focuses on the removal of the masonry pillar from the front wall of an apartment house. The masonry pillar should be replaced with two steel columns in a given axis distance. The parts of the thesis are a technical report, a static calculation and a graphic documentation. The description of the current object and the proposed solution is included within the technical report. The static calculation deals with a calculation of the strain and the enhancement of the current ferroconcrete lintel on the ground and first floor. A proposal of the solution, which is determined by the static calculation, is evident from the graphic documentary.
|
|
|
Modification of Company Information System
Došek, Ivan ; Ondrovič, Ing Michal (referee) ; Koch, Miloš (advisor)
Bachelor thesis focuses on the enhancement and improvement of work with the data to be inserted into the database, due to more efficient work. Report data being generated by my software, where user will have to log in to see when and where the individual sees training and training of subordinates. The system is intended to replace the current inadequate and hardly maintainable condition momentary record of training in opaque Excel spreadsheets
|
|
|
Identification of Speech Activity in Noisy Speech Signal
Pelikán, Martin ; Sysel, Petr (referee) ; Smékal, Zdeněk (advisor)
This paper is focused on identification of pauses in noisy speech signal and following filtering of the noise from the signal. Firstly the signal processing methods are theoretically described, then voice activity detectors and in the end noise filtering methods are described. Several voice activity detectors were created and their pause detection rate was compared.
|
|
|
Automatic detection of neural fibers losses
Václavek, Martin ; Jiřík, Radovan (referee) ; Kolář, Radim (advisor)
This work is focused on detection of loss in nerve fibre layer on colour pictures of retina, witch are makes by fundus camera. It describe every simple objects of retina, optic nerve head, macula lutea and vascular bed. It detect optic nerve head and his near area, witch is general for detection of breakdownds. It use several metodes of picture adjusting for picture elaboration and objects detection (segmentation, thresholding, enhancement, hough transformation ). The detection of loss in nerve fibre layer is based on comparing of statistic parameters ( average, standart deviation, skewness coefficient and kurtosis coefficient histogram, entropy ) in choosed areas with and withou destruction of nerve layers. Vascular bed have badwatsh on results, cause of this we using hand choosing of essay.
|
|
|
Segmentation in the color fundus imges
Malínský, Miloš ; Jiřík, Radovan (referee) ; Kolář, Radim (advisor)
Optic nerve head and macula are important structures in fundus images. Detection and measurement plays crucial role in several diagnosis methods of optic disease. This work is focused on the detection of the central point of macula and optic nerve head, where the inner border is detected too. There are many methods for extracting this structure in retinal images. Due to the unique properties of each acquisition technique, a single generally acknowledged detection algorithm does not exist. The whole detection process is described from preprocessing through segmentation towards postprocessing. Presented methods are based on the combination of correlation techniques, Hough transform, active contours and morphological operations. The detected contours of the optic nerve head are evaluated and quantitatively compared with the contour drawn by experienced ophthalmologist. The master thesis contains quantity of images that help to describe detection methods.
|
|
|
Specifics of Data Warehouse enhancement in a bank
Karásek, Tomáš ; Pour, Jan (advisor) ; Hylmarová, Lenka (referee)
The present thesis deals with the specifics of Data Warehouse enhancement in a bank. The aim of the thesis is a definition of the general specifics of banks, their Business Intelligence and Data Warehouse enhancement compared to other companies. The thesis is divided into seven parts. The first part describes the theoretical basis of banking and Business Intelligence. The second part defines the general specifics of banks and their informatics compared to other companies. Then Business Intelligence in a bank, its architecture and enhancement are explored. In the fourth part a conceptual data model of Data Warehouse in a bank is introduced and described in detail. Afterwards the main source systems of Data Warehouse are identified and matched to the subject areas of the data model. The sixth part discovers important application areas of Business Intelligence usage and mentions the basic indicators. The last part presents a case study (a project of Data Warehouse enhancement in a bank). The result of this thesis is clear description of the Data Warehouse in a bank, its data model, source systems, application areas and enhancement.
|
|
|
Optimization of the amount of iodine contrast agent (ICU) in CT scan examinations on a multislice CT scanner (64-detector row)
KRAJÍČEK, Ondřej
In my work, I focused on the optimization of the amount of iodine contrast agent during CT scan examinations by comparing various amounts of the contrast agent per kilogram of a patient{\crq}s body weight. I compared three groups of weight amounts: 1 mL/kg vs. 1.25 mL/kg vs. 1.5 mL/kg. I measured the differences in the enhancement of organs and blood vessels of the abdominal cavity. Their enhancement levels were compared quantitatively in the areas of interest by determining Hounsfield units in the aorta and parenchyma of the abdominal organs, and qualitatively by using an independent evaluation by a radiologist. Measurements were made on the GE Lightspeed 64-detector row CT scanner with pressure injector. No parameters were changed during the entire study, enabling the maintenance of standard conditions for high-quality comparisons in all examinations. Patients with any significant lesion in the organ to be measured were excluded from the study measurements, and patients at risk of circulation disorder (patients with severe conditions, such as heart failure, shock, and others) were also not enrolled. A contrast agent with a constant amount of iodine amounting to 300 mg/mL was used for the measurements. The study population comprised 120 patients, of which 51 were women and 69 men. The following data were recorded for each measurement: examination number, age, sex, body weight, HU values, and radiologist{\crq}s evaluation. The data were recorded in tables and further analyzed. Various HU enhancement levels were compared and evaluated and subsequently correlated with the radiologist{\crq}s evaluation. Optimal values of the amount of contrast agent were also compared with those routinely used at the facility concerned. This work provided optimal values of the amount of contrast agent for the examination of abdominal organs and adjusted standards for a CT scan facility. I believe my bachelor{\crq}s thesis contributed to a more precise dosing of the contrast agent during CT scan examinations.
|
guest ::
