Data compression is a challenging process with important practical applications. Specialized techniques for lossy and lossless data compression have been the subject of numerous investigations during last several deca...
详细信息
Data compression is a challenging process with important practical applications. Specialized techniques for lossy and lossless data compression have been the subject of numerous investigations during last several decades. Previously, we studied the use of the pseudo-distance technique (PDT) in lossless compression of color-mapped images and its parallel implementation. In this paper we present a new technique (PDT2) to improve compression gain of PDT. We also present a parallelized implementation of the new technique, which results in substantial gains in compression time while providing the desired compression efficiency. We demonstrate that on non-dithered images PDT2 outperforms PDT by 22.4% and PNG by 29.3%. On dithered images, PDT2 achieves compression gains of 7.1% over PDT and 23.8% over PNG. We also show that the parallel implementation of PDT2, while compromising compression less than 0.3%, achieves near linear speedup and utilization of Intel Hyper-Threading technology on supported systems improves speedup on average 18%. (C) 2015 Elsevier Ltd. All rights reserved.
imagecompression has a number of applications in various fields, where processing throughput and/or latency is a crucial attribute and the main limitation of state-of-the-art implementations of compression algorithms...
详细信息
ISBN:
(纸本)9780819492166
imagecompression has a number of applications in various fields, where processing throughput and/or latency is a crucial attribute and the main limitation of state-of-the-art implementations of compression algorithms. At the same time contemporary GPU platforms provide tremendous processing power but they call for specific algorithm design. We discuss key components of successful design of compression algorithms for GPUs and demonstrate this on JPEG and JPEG2000 implementations, each of which contains several types of algorithms requiring different approaches to efficient parallelization for GPUs. Performance evaluation of the optimized JPEG and JPEG2000 chain is used to demonstrate the importance of various aspects of GPU programming, especially with respect to real-time applications
The Graphic Processing Unit (GPU) is increasingly becoming an important alternative for many applications that requires real time parallel processing. More interestingly, digital image processing applications such as ...
详细信息
ISBN:
(纸本)9780769543529
The Graphic Processing Unit (GPU) is increasingly becoming an important alternative for many applications that requires real time parallel processing. More interestingly, digital image processing applications such as imagecompression are becoming closer than ever of being processed in real time. In this paper we explore the implementation of DCT on the GPUs. Our study indicates a clear superiority of the GPU as parallel processor for imagecompression using DCT over the CPU. Our study also indicates that the increase in image size has considerably slows the CPU while the GPU was not affected.
暂无评论