Design and realization of high-performance wave-pipelined 8 × 8 b multiplier in CMOS technology
IEEE Transactions on Very Large Scale Integration (VLSI) Systems
A pipelined architecture for partitioned DWT based lossy image compression using FPGA's
FPGA '01 Proceedings of the 2001 ACM/SIGDA ninth international symposium on Field programmable gate arrays
Optimization techniques for FPGA-based wave-pipelined DSP blocks
IEEE Transactions on Very Large Scale Integration (VLSI) Systems
Wave-pipelining: a tutorial and research survey
IEEE Transactions on Very Large Scale Integration (VLSI) Systems
A wavelet-based region of interest encoder for the compression of angiogram video sequences
IEEE Transactions on Information Technology in Biomedicine
Embolic Doppler ultrasound signal detection using discrete wavelet transform
IEEE Transactions on Information Technology in Biomedicine
Accelerated image processing on FPGAs
IEEE Transactions on Image Processing
Hi-index | 0.00 |
In this paper, a hybrid scheme is proposed for the implementation of two level 2D-DWT using lifting scheme. Two filter banks consisting of two filters each are used for the implementation of both horizontal and vertical filters. Each of the filter banks are implemented using the lifting scheme. The individual lifting blocks are implemented using wavepipelining and are interconnected with registers. An automation procedure is proposed for tuning the parameters of the wavepipelined circuit. The multipliers in the lifting blocks are implemented using Baugh-Wooley constant coefficient multiplier scheme (BW-KCM). For verifying the efficacy of the scheme proposed, both one level and two level 2-D DWT schemes for sub images of size 32×32 are implemented on Xilinx XC2S150 device. The results for the hybrid scheme are compared with that obtained using non-pipelined and pipelined approaches. For the one level 2D DWT, the hybrid scheme requires the same area but is faster than nonpipelined scheme by a factor of 1.4. The pipelined scheme using the pipelined BW-PKCM is faster than the hybrid scheme by a factor of 1.2 at the cost of increase in the no. of registers by a factor of 2.73. The delay-power product is lower for hybrid scheme by a factor of 2 than the pipelined scheme. The two level 2D DWT for both pipelined and non pipelined schemes are implemented. The implementation of hybrid scheme for 2 level 2 D DWT is under progress. The technique proposed in this paper is also applicable for ASICs and FPGAs from other vendors.