Parallel FPGA Implementation of the Split and Merge Discrete Wavelet Transform

The discrete wavelet transform has become a highly effective tool in many signal processing and data compression applications. In fact, it is widely accepted that JPEG2000, with its wavelet based image-coding technology will become the universally accepted format for digital images - whether on the web, over wireless systems, in digital cameras, printers, faxes or remote sensors. Various hardware implementations of the DWT were proposed by researchers to reduce its complexity and enhance its performance. In this paper we present an efficient hardware implementation of the discrete wavelet transform suitable for deployment on a reconfigurable FPGA based platform. Our implementation is a novel architecture based on the lifting factorization of the wavelet filter banks that uses the Overlap-State algorithm. It minimizes, memory usage, computational complexity, and communication overhead associated with parallel implementations.

[1]  Geert Uytterhoeven.  Wavelets: software and applications , 1999 .

[2]  Sethuraman Panchanathan,et al.  VLSI implementation of discrete wavelet transform , 1996, IEEE Trans. Very Large Scale Integr. Syst..

[3]  Stéphane Mallat,et al.  A Theory for Multiresolution Signal Decomposition: The Wavelet Representation , 1989, IEEE Trans. Pattern Anal. Mach. Intell..

[4]  C. Brislawn.  Classification of Nonexpansive Symmetric Extension Transforms for Multirate Filter Banks , 1996 .

[5]  Todd M. Austin,et al.  The SimpleScalar tool set, version 2.0 , 1997, CARN.

[6]  Gabriel Fernandez,et al.  LIFTPACK: a software package for wavelet transforms using lifting , 1996, Optics & Photonics.

[7]  William H. Press,et al.  Numerical Recipes: FORTRAN , 1988 .

[8]  I. Daubechies,et al.  Factoring wavelet transforms into lifting steps , 1998 .

[9]  Kang Hyeon Rhee,et al.  FPGA implementation of subband image encoder using discrete wavelet transform , 1999, Proceedings of IEEE. IEEE Region 10 Conference. TENCON 99. 'Multimedia Technology for Asia-Pacific Information Infrastructure' (Cat. No.99CH37030).

[10]  Wim Sweldens,et al.  Lifting scheme: a new philosophy in biorthogonal wavelet constructions , 1995, Optics + Photonics.

[11]  M.D. Adams,et al.  Wavelet transforms in the JPEG-2000 standard , 2001, 2001 IEEE Pacific Rim Conference on Communications, Computers and Signal Processing (IEEE Cat. No.01CH37233).

[12]  A.M. Reza,et al.  FPGA implementation of 2D wavelet transform , 1999, Conference Record of the Thirty-Third Asilomar Conference on Signals, Systems, and Computers (Cat. No.CH37020).

[13]  W. Sweldens.  The Lifting Scheme: A Custom - Design Construction of Biorthogonal Wavelets "Industrial Mathematics , 1996 .

[14]  Antonio Ortega,et al.  Parallel architecture for the discrete wavelet transform based on the lifting factorization , 1999, Optics + Photonics.

[15]  Stamatis Vassiliadis,et al.  Coarse reconfigurable multimedia unit extension , 2001, Proceedings Ninth Euromicro Workshop on Parallel and Distributed Processing.

[16]  Prarthana Shrestha,et al.  MIPS Augmented with Wavelet Transform: Performance Analysis , 2002 .

[17]  Stamatis Vassiliadis,et al.  The MOLEN ρμ-coded processor , 2001 .