DocumentCode :
2007471
Title :
An Efficient Algorithm for 9-7 Discrete Wavelet Transform Based on Fragment Look-up Table
Author :
Chen, Dake ; Han, Jiuqiang ; Yang, Lei
Author_Institution :
Xian Jiaotong Univ., Xian
fYear :
2007
fDate :
May 30 2007-June 1 2007
Firstpage :
2017
Lastpage :
2020
Abstract :
An efficient algorithm for 9/7 discrete wavelet transform based on fragment look-up table (LUT) is studied in the paper. The algorithm implements the wavelet transform by time-sharing LUT and operation with small memory, and it farthest eliminates the hardware resource necessary for multiplication operation while ensuring operation precision and speed. The problem of combining segmented data to realize high precision multiplication operation is solved. Compared with multiplication operation, the fragment LUT operation is simpler and faster, and can be implemented easily by VLSI. The algorithm is verified on Altera´s FLEX10K30 FPGA. And the result shows the performance of the algorithm: with only 256 times 8 bits on-chip RAM, and the calculation precision is up to 14 -bit binary, the transform time can be up to 74 ns. So using the fragment LUT to implement wavelet transform is faster than using algorithms implemented in general logic.
Keywords :
VLSI; discrete wavelet transforms; field programmable gate arrays; system-on-chip; table lookup; 9-7 discrete wavelet transform; FPGA; VLSI; field programmable gate array; fragment look-up table; multiplication operation; onchip RAM; Discrete wavelet transforms; Field programmable gate arrays; Filters; Hardware; Image coding; Read-write memory; Table lookup; Transform coding; Very large scale integration; Wavelet transforms; FPGA; discrete wavelet transform; fragment look-up table; lifting scheme;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Control and Automation, 2007. ICCA 2007. IEEE International Conference on
Conference_Location :
Guangzhou
Print_ISBN :
978-1-4244-0818-4
Electronic_ISBN :
978-1-4244-0818-4
Type :
conf
DOI :
10.1109/ICCA.2007.4376714
Filename :
4376714
Link To Document :
بازگشت