Design and Implementation of Modified Distributive Arithmetic Based DWT Architecture Using FPGA

Abstract:

This paper presents a modified distributive arithmetic based DWT architecture and is implemented in FPGA. The modified DA-DWT architecture has a latency of 44 clock cycles and a throughput of 4 clock cycles. This design is twice faster than the reference design and is thus suitable for applications that require high speed image processing algorithms. In this paper, reliable and high speed DWT architecture is designed and implemented in FPGA which can be used as a co-processor for image compression and decompression. The bi-orthogonal wavelets, with different number of coefficients in the low pass and high pass filters, increase the number of operations and the complexity of the design, but they have better SNR than the orthogonal filters. The code has been written in VHDL and implemented on the FPGA using a 32 x 32 random image. This architecture enables fast computation of DWT with parallel processing. It has low memory requirements and consumes low power. This architecture is faster than the existing architectures as the latency is reduced by half clock cycles and through put is increased by a factor of 2.

• Periodical: Applied Mechanics and Materials (Volume 550)
• Pages: 172-177
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.550.172
• Online since: May 2014
• Authors: S. Senthil Kumar*, R. Radhakrishnan, K. Priyadharshini
• Keywords: Discrete Wavelet Transform (DWT), Distributive Arithmetic, Lifting Scheme

References

[1] W. Sweldens, The lifting scheme: A custom-design construction of bi-orthogonal wavelets, Applied and Computational Harmonic Analysis, vol. 3, no. 2, p.186–200, (1996).

DOI: 10.1006/acha.1996.0015

[2] P. -C. Wu and L. -G. Chen, An efficient architecture for two-dimensional discrete wavelet transform, IEEE Trans. Circuits and Systems for Video Technology, vol. 11, no. 4, p.536–545, Apr. (2001).

DOI: 10.1109/76.915359

[3] Nagabushanam, Cyril Prasanna Raj P, Ramachandran, Design and implementation of Parallel and Pipelined Distributive Arithmetic based Discrete Wavelet Transform IP core, EJSR, Vo. 35, No. 3, pp.378-392, (2009).

DOI: 10.1109/iccsp.2011.5739397

[4] Mintzer, L. 1996. The Role of Distributed Arithmetic in FPGAs,. Xilinx Corporation.

[5] M. Al-Haj, Fast discrete wavelet transformation using FPGAs and distributed arithmetic, International Journal of Applied Science and Engineering, vol. 1, no. 2, pp.160-171, (2003).

[6] Knowles, G. VLSI architecture for the discrete wavelet transform, Electron Letters, 26, 15: 1184-1185, (1990).

DOI: 10.1049/el:19900766

[7] Parhi, K. and Nishitani, T. VLSI architectures for discrete wavelet transform, IEEE Transactions on VLSI Systems, pp.191-202, (1993).

DOI: 10.1109/92.238416

[8] Chakabarti, C. and Vishwanath, M. Efficient realizations of the discrete and continuous wavelet transforms: from single chip implementations to mappings on SIMD array computers, IEEE Transactions on Signal Processing, 43, 3: 759-771, (1995).

DOI: 10.1109/78.370630