|
Lossless Image Compression Using Wavelet Transform
Tumpach, Jiří ; Polok, Lukáš (referee) ; Bařina, David (advisor)
This work focuses on wavelet transform and its use in image compression particularly on a comparation between classical tensor product wavelets and new kind of second generation wavelet also known as red-black wavelet transform. Although brief comparison of EBCOT modifications, color transforms, wavelets and predictors are discussed too. A framework for an evaluation of some current methods is constructed and results across different image groups are presented. In addition, C++ library was created. Proposed lossless compression methods are better then JPEG 2000 and PNG.
|
|
Online training of deep neural networks for classification
Tumpach, Jiří ; Holeňa, Martin (advisor) ; Kořenek, Jakub (referee)
Deep learning is usually applied to static datasets. If used for classification based on data streams, it is not easy to take into account a non-stationarity. This thesis presents work in progress on a new method for online deep classifi- cation learning in data streams with slow or moderate drift, highly relevant for the application domain of malware detection. The method uses a combination of multilayer perceptron and variational autoencoder to achieve constant mem- ory consumption by encoding past data to a generative model. This can make online learning of neural networks more accessible for independent adaptive sys- tems with limited memory. First results for real-world malware stream data are presented, and they look promising. 1
|
|
Lossless Image Compression Using Wavelet Transform
Tumpach, Jiří ; Polok, Lukáš (referee) ; Bařina, David (advisor)
This work focuses on wavelet transform and its use in image compression particularly on a comparation between classical tensor product wavelets and new kind of second generation wavelet also known as red-black wavelet transform. Although brief comparison of EBCOT modifications, color transforms, wavelets and predictors are discussed too. A framework for an evaluation of some current methods is constructed and results across different image groups are presented. In addition, C++ library was created. Proposed lossless compression methods are better then JPEG 2000 and PNG.
|