|
| |
|
|
Texture Synthesis
Sousedík, Ctirad ; Štancl, Vít (referee) ; Španěl, Michal (advisor)
This Bachelor's thesis deals with automatic texture synthesis. The main objective is to develop the best possible method of texture synthesis, inclusive a graphical demonstration utility. The original concept, developed by Li-Yi Wei and Marc Lewoy, Stanford University, has been modified to achieve better results. A method of detecting specific structures within texture images has been developed to initialize a synthesized image, and improve the final result. The employed algorithms are foolproof, and only limited numbers of input parameters have to be tuned.
|
|
|
Texture modeling applied to medical images
Remeš, Václav ; Haindl, Michal (advisor)
and contributions This thesis presents novel descriptive multidimensional Markovian textural models applied to computer aided diagnosis in the field of X-ray mammogra- phy. These general mathematical models, applicable in wide areas of texture modeling outside X-ray mammography as well, provide ideal visual verification using synthesis of the corresponding measured data spaces, contrary to stan- dard discriminative models. All achieved results in the thesis are extensively benchmarked. The thesis presents two methods for breast density classification in X-ray mammography. The methods were tested on the widely known MIAS database and the state-of-the art INbreast database, with competitive results. Several methods for completely automatic mammogram texture enhance- ment are presented. These methods are based on the descriptive textural mod- els developed in the thesis which automatically adapt to the analyzed X-ray texture, thus being universal for any type of input without the need of further manual tuning of specific parameters. The methods' outputs highlight regions of interest, detected as textural abnormalities. The methods provide the pos- sibility of enhancement tuned to specific types of mammogram tissue. Hence, the enhanced mammograms can help radiologists to decrease their false negative...
|
|
|
Procedural building reconstruction from building outlines
Kužel, Vojtěch ; Kahoun, Martin (advisor) ; Beneš, Jan (referee)
This thesis presents a method for fast procedural generation of plausible buildings out of their outlines. There are a few methods in existence varying in their speed and in the amount of detail in their results. All of these methods can be utilized on diverse occasions. The user might prefer speed over complexity or maybe better-looking results over robustness to every input. The method presented in this thesis prefers speed and semi-automatic approach. It takes building outlines as an input along with some user defined parameters such as height, reconstructs the building mass with a general hip roof, and synthetizes plausible textures. The results can be then used for example in flight simulators for fast reconstruction of large urban areas based on the data available through, e.g., Open Street Maps.
|
|
|
Texture modeling applied to medical images
Remeš, Václav ; Haindl, Michal (advisor)
and contributions This thesis presents novel descriptive multidimensional Markovian textural models applied to computer aided diagnosis in the field of X-ray mammogra- phy. These general mathematical models, applicable in wide areas of texture modeling outside X-ray mammography as well, provide ideal visual verification using synthesis of the corresponding measured data spaces, contrary to stan- dard discriminative models. All achieved results in the thesis are extensively benchmarked. The thesis presents two methods for breast density classification in X-ray mammography. The methods were tested on the widely known MIAS database and the state-of-the art INbreast database, with competitive results. Several methods for completely automatic mammogram texture enhance- ment are presented. These methods are based on the descriptive textural mod- els developed in the thesis which automatically adapt to the analyzed X-ray texture, thus being universal for any type of input without the need of further manual tuning of specific parameters. The methods' outputs highlight regions of interest, detected as textural abnormalities. The methods provide the pos- sibility of enhancement tuned to specific types of mammogram tissue. Hence, the enhanced mammograms can help radiologists to decrease their false negative...
|
|
|
Texture Synthesis
Sousedík, Ctirad ; Štancl, Vít (referee) ; Španěl, Michal (advisor)
This Bachelor's thesis deals with automatic texture synthesis. The main objective is to develop the best possible method of texture synthesis, inclusive a graphical demonstration utility. The original concept, developed by Li-Yi Wei and Marc Lewoy, Stanford University, has been modified to achieve better results. A method of detecting specific structures within texture images has been developed to initialize a synthesized image, and improve the final result. The employed algorithms are foolproof, and only limited numbers of input parameters have to be tuned.
|
|
| |
guest ::
