Share Email Print
cover

Proceedings Paper

A high-throughput two channel discrete wavelet transform architecture for the JPEG2000 standard
Author(s): Hossein Badakhshannoory; Mahmoud Reza Hashemi; Alireza Aminlou; Omid Fatemi
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper Abstract

The Discrete Wavelet Transform (DWT) is increasingly recognized in image and video compression standards, as indicated by its use in JPEG2000. The lifting scheme algorithm is an alternative DWT implementation that has a lower computational complexity and reduced resource requirement. In the JPEG2000 standard two lifting scheme based filter banks are introduced: the 5/3 and 9/7. In this paper a high throughput, two channel DWT architecture for both of the JPEG2000 DWT filters is presented. The proposed pipelined architecture has two separate input channels that process the incoming samples simultaneously with minimum memory requirement for each channel. The architecture had been implemented in VHDL and synthesized on a Xilinx Virtex2 XCV1000. The proposed architecture applies DWT on a 2K by 1K image at 33 fps with a 75 MHZ clock frequency. This performance is achieved with 70% less resources than two independent single channel modules. The high throughput and reduced resource requirement has made this architecture the proper choice for real time applications such as Digital Cinema.

Paper Details

Date Published: 24 June 2005
PDF: 8 pages
Proc. SPIE 5960, Visual Communications and Image Processing 2005, 596048 (24 June 2005); doi: 10.1117/12.632673
Show Author Affiliations
Hossein Badakhshannoory, Univ. of Tehran (Iran)
Mahmoud Reza Hashemi, Univ. of Tehran (Iran)
Alireza Aminlou, Univ. of Tehran (Iran)
Omid Fatemi, Univ. of Tehran (Iran)


Published in SPIE Proceedings Vol. 5960:
Visual Communications and Image Processing 2005
Shipeng Li; Fernando Pereira; Heung-Yeung Shum; Andrew G. Tescher, Editor(s)

© SPIE. Terms of Use
Back to Top