National Repository of Grey Literature 3 records found  Search took 0.00 seconds. 
Picture correction
Sedlo, Petr ; Horák, Karel (referee) ; Richter, Miloslav (advisor)
This work is focussed on different unwanted effects that damage a digitally acquired image. An image acquired using a digital camera can suffer from a series of defects. First, the noise is concerned. It occures due to discretisation. Next, there are the defects including vignetting, radial image distortion, chromatic aberration. In my thesis I also worked on backlight image compensation and panorama creation from an image sequence. For backlight images we need to increase the brightness in the dark parts of the image, so that the details became more visible. At panorama creation we are careful about brightness evenness in partial images, which is usually not conserved and consequently we try to find a suitable boundary-line to connect images and smooth it. The fundamental part of my work was writing the algorithms that are able to compensate these defects at least partly. For this aim I took use of the Matlab environment.
Hybrid Application for Calibration of Camera Lenses
Dovhalenko, Dmytro ; Malaník, Petr (referee) ; Šimek, Václav (advisor)
The goal of this bachelor’s thesis is to design and implement a tool for correction of image distortion caused by the physical curvature of a fisheye camera lens. The theoretical part is concerned with available solutions analysis in order to find an image distortion correction tool that uses modern technologies. The technologies are analyzed and described to find alternative points of view resulting in a way to change software delivery process and deliver a tool in the form of a web application. The thesis takes into account the necessity to deliver a tool that can be developed and deployed in a context of corporate environment. It focuses on the issue of generating settings for hardware-accelerated image correction since it is used more frequently in the real world than its software counterpart. The practical part analyzes various usage scenarios, suitable architecture design as well as user environment design. To achieve this, hybrid web technologies in combination with OpenCV library in the form of a web assembly, as well as other modern tools such as SSO authentication and browser’s built-in storage are used. This thesis will benefit mostly customers in need of modern image distortion calibration solutions. It proves that it is possible to use hybrid web applications to deliver native application alternative that simultaneously increases user comfort. The thesis also provides data important for transformation of native applications into hybrid web applications.
Picture correction
Sedlo, Petr ; Horák, Karel (referee) ; Richter, Miloslav (advisor)
This work is focussed on different unwanted effects that damage a digitally acquired image. An image acquired using a digital camera can suffer from a series of defects. First, the noise is concerned. It occures due to discretisation. Next, there are the defects including vignetting, radial image distortion, chromatic aberration. In my thesis I also worked on backlight image compensation and panorama creation from an image sequence. For backlight images we need to increase the brightness in the dark parts of the image, so that the details became more visible. At panorama creation we are careful about brightness evenness in partial images, which is usually not conserved and consequently we try to find a suitable boundary-line to connect images and smooth it. The fundamental part of my work was writing the algorithms that are able to compensate these defects at least partly. For this aim I took use of the Matlab environment.

Interested in being notified about new results for this query?
Subscribe to the RSS feed.