|
|
Vector Graphics Output from an HTML Rendering Engine
Chocholatý, Tomáš ; Rychlý, Marek (referee) ; Burget, Radek (advisor)
This thesis focuses on the issue of rendering web pages using vector graphics. The experimental CSSBox display engine and existing libraries for rendering vector graphics in PDF and SVG will be described here. The goal of the thesis is design a common structure for these two libraries and unify the process of rendering web pages in vector graphics as much as possible. Analysis of incorrectly implemented parts of existing solutions will be performed here and shortcomings, which will be necessary to implement to the resulting vector graphic meet the standard CSS3, will be describe. Furthermore, the implementation process, including the repair of all non-functioning original solutions, and the principle of unification of individual parts for the generation of both vector formats will be described. The conclusion is dedicated the results of self testing and outputs from generating real websites.
|
|
|
Detection of Traffic Signs and Lights
Chocholatý, Tomáš ; Bartl, Vojtěch (referee) ; Herout, Adam (advisor)
The thesis focuses on traffic sign detection and traffic lights detection in view with utilization convolution neural network. The goal is create suitable detector for detection and classification traffic sign in real traffic. For training of convolution neural network were created appropriate datasets, that contains synthetic and real dataset. For synthetic dataset was create generator, that can simulated different deformation of traffic signs. Evaluation is done by own program for quantitative evaluation. The detection rate successfully detected signs is 89\% over own test dataset. The results allow to find out importance of representation real or synthetic dataset in training dataset and influence individual deformations synthetic dataset for final detection quality.
|
|
|
Vector Graphics Output from an HTML Rendering Engine
Chocholatý, Tomáš ; Rychlý, Marek (referee) ; Burget, Radek (advisor)
This thesis focuses on the issue of rendering web pages using vector graphics. The experimental CSSBox display engine and existing libraries for rendering vector graphics in PDF and SVG will be described here. The goal of the thesis is design a common structure for these two libraries and unify the process of rendering web pages in vector graphics as much as possible. Analysis of incorrectly implemented parts of existing solutions will be performed here and shortcomings, which will be necessary to implement to the resulting vector graphic meet the standard CSS3, will be describe. Furthermore, the implementation process, including the repair of all non-functioning original solutions, and the principle of unification of individual parts for the generation of both vector formats will be described. The conclusion is dedicated the results of self testing and outputs from generating real websites.
|
|
|
Detection of Traffic Signs and Lights
Chocholatý, Tomáš ; Bartl, Vojtěch (referee) ; Herout, Adam (advisor)
The thesis focuses on traffic sign detection and traffic lights detection in view with utilization convolution neural network. The goal is create suitable detector for detection and classification traffic sign in real traffic. For training of convolution neural network were created appropriate datasets, that contains synthetic and real dataset. For synthetic dataset was create generator, that can simulated different deformation of traffic signs. Evaluation is done by own program for quantitative evaluation. The detection rate successfully detected signs is 89\% over own test dataset. The results allow to find out importance of representation real or synthetic dataset in training dataset and influence individual deformations synthetic dataset for final detection quality.
|
guest ::
