DocumentCode
2736296
Title
An efficient VLSI implementation of DWT for JPEG2000
Author
Zhu, Ke ; Zhou, Xiao-Fang ; Hua, Lin ; Zhang, Qian-ling
Author_Institution
ASIC & Syst. State Key Lab., Fudan Univ., Shanghai, China
Volume
2
fYear
2003
fDate
14-17 Dec. 2003
Firstpage
990
Abstract
This paper proposed an efficient VLSI architecture for lifting-based Discrete Wavelet Transformation (DWT) recommended by JPEG2000. The architecture included the basic processing element (PE) and the memory control unit (MCU) and the memory modules. The finite precision analysis has been carried out and the data path width was fixed at 20bis. The memory module included fourteen basic memory units. Ten of them were used to the DWT processing and the residual four units was used to entropy coding. The MCU was in charge of the memory access and set up a pipelining processing between the DWT and entropy coding in JPEG2000. The architecture has default filters to generate an output every cycle for JPEG2000. The architecture has been implemented in behavioral Verilog. The estimated gates of our proposed architecture in SIMC 0.18-/spl mu/m technology are 6600 and the estimated frequency of operation is 300 Mhz.
Keywords
VLSI; discrete wavelet transforms; filters; hardware description languages; image coding; modules; pipeline processing; 0.18 micron; 300 MHz; JPEG2000; VLSI architecture; entropy coding; filters; finite precision analysis; frequency estimation; lifting based discrete wavelet transformation; memory control unit; memory modules; pipelining processing; processing element; verilog; very large scale integration; Application specific integrated circuits; Discrete wavelet transforms; Entropy coding; Filters; Frequency estimation; Hardware design languages; Laboratories; Pipeline processing; Transform coding; Very large scale integration;
fLanguage
English
Publisher
ieee
Conference_Titel
Neural Networks and Signal Processing, 2003. Proceedings of the 2003 International Conference on
Conference_Location
Nanjing
Print_ISBN
0-7803-7702-8
Type
conf
DOI
10.1109/ICNNSP.2003.1281035
Filename
1281035
Link To Document