GPU-Based Implementation of JPEG2000 Encoder
Department of Computer Engineering and IT, Hamedan University of Technology, Hamedan, Iran
The 2012 International Conference on Parallel and Distributed Processing Techniques and Applications (PDPTA’12), 2012
@article{ahmadvand2012gpu,
title={GPU-Based Implementation of JPEG2000 Encoder},
author={Ahmadvand, M. and Ezhdehakosh, A.},
year={2012}
}
JPEG2000 has become one of the most rewarding image coding standards. It provides a practical set of features which weren’t necessarily available in the previous standards. The features were realized as a result of two new techniques, namely the Discrete Wavelet Transform (DWT), and Embedded Block Coding with Optimized Truncation (EBCOT). The complexity of EBCOT Tier-1 makes its implementations very difficult and time consuming. In this paper, we focus on accelerating JPEG2000 encoder by using general-purpose processing on Graphical Processing Unit (GPU). We use CUDA platform to implement DWT and EBCOT Tier-1 as the most important sections of JPEG2000. Resulting implementation of proposed architecture performs very well compared to other available implementations.
December 3, 2012 by hgpu
