TY - JOUR
T1 - Design and analysis of high-throughput lossless image compression engine using VLSI-oriented FELICS algorithm
AU - Tsai, Tsung Han
AU - Lee, Yu Hsuan
AU - Lee, Yu Yu
N1 - Funding Information:
Manuscript received March 28, 2008; revised August 01, 2008. First published March 27, 2009; current version published December 23, 2009. This work was supported in part by the National Science Council, Taiwan, under Grant 96-2220-E-008-006.
PY - 2010/1
Y1 - 2010/1
N2 - In this paper, the VLSI-oriented fast, efficient, lossless image compression system (FELICS) algorithm, which consists of simplified adjusted binary code and Golomb-Rice code with storage-less parameter selection, is proposed to provide the lossless compression method for high-throughput applications. The simplified adjusted binary code reduces the number of arithmetic operation and improves processing speed. According to theoretical analysis, the storage-less parameter selection applies a fixed value in Golomb-Rice code to remove data dependency and extra storage for cumulation table. Besides, the color difference preprocessing is also proposed to improve coding efficiency with simple arithmetic operation. Based on VLSI-oriented FELICS algorithm, the proposed hardware architecture features compactly regular data flow, and two-level parallelism with four-stage pipelining is adopted as the framework of the proposed architecture. The chip is fabricated in TSMC 0.13-μm 1P8M CMOS technology with Artisan cell library. Experiment results reveal that the proposed architecture presents superior performance in parallelism-efficiency and power-efficiency compared with other existing works, which characterize high-speed lossless compression. The maximum throughput can achieve 4.36 Gb/s. Regarding high definition (HD) display applications, our encoding capability can achieve a high-quality specification of full-HD 1080p at 60 Hz with complete red, green, blue color components. Furthermore, with the configuration as the multilevel parallelism, the proposed architecture can be applied to the advanced HD display specifications, which demand huge requirement of throughput.
AB - In this paper, the VLSI-oriented fast, efficient, lossless image compression system (FELICS) algorithm, which consists of simplified adjusted binary code and Golomb-Rice code with storage-less parameter selection, is proposed to provide the lossless compression method for high-throughput applications. The simplified adjusted binary code reduces the number of arithmetic operation and improves processing speed. According to theoretical analysis, the storage-less parameter selection applies a fixed value in Golomb-Rice code to remove data dependency and extra storage for cumulation table. Besides, the color difference preprocessing is also proposed to improve coding efficiency with simple arithmetic operation. Based on VLSI-oriented FELICS algorithm, the proposed hardware architecture features compactly regular data flow, and two-level parallelism with four-stage pipelining is adopted as the framework of the proposed architecture. The chip is fabricated in TSMC 0.13-μm 1P8M CMOS technology with Artisan cell library. Experiment results reveal that the proposed architecture presents superior performance in parallelism-efficiency and power-efficiency compared with other existing works, which characterize high-speed lossless compression. The maximum throughput can achieve 4.36 Gb/s. Regarding high definition (HD) display applications, our encoding capability can achieve a high-quality specification of full-HD 1080p at 60 Hz with complete red, green, blue color components. Furthermore, with the configuration as the multilevel parallelism, the proposed architecture can be applied to the advanced HD display specifications, which demand huge requirement of throughput.
KW - Full high-definition (HD) 1080p
KW - Lossless compression
KW - Parallelism
KW - VLSI architecture
UR - http://www.scopus.com/inward/record.url?scp=73249130440&partnerID=8YFLogxK
U2 - 10.1109/TVLSI.2008.2007230
DO - 10.1109/TVLSI.2008.2007230
M3 - 期刊論文
AN - SCOPUS:73249130440
SN - 1063-8210
VL - 18
SP - 39
EP - 52
JO - IEEE Transactions on Very Large Scale Integration (VLSI) Systems
JF - IEEE Transactions on Very Large Scale Integration (VLSI) Systems
IS - 1
M1 - 4806140
ER -