Residue number system for two-dimensional discrete wavelet transform

Discrete wavelet transform (DWT) is the core image processing method used in JPEG 2000 Coding System. Currently, there are many DWT processing unit designed in Binary Number system. This project involves designing the first two-dimensional lifting-based DWT architecture in Residue Number System (RNS...

全面介紹

Saved in:
書目詳細資料
主要作者: Tay, Thian Fatt.
其他作者: Chang Chip Hong
格式: Final Year Project
語言:English
出版: 2011
主題:
在線閱讀:http://hdl.handle.net/10356/45724
標簽: 添加標簽
沒有標簽, 成為第一個標記此記錄!
實物特徵
總結:Discrete wavelet transform (DWT) is the core image processing method used in JPEG 2000 Coding System. Currently, there are many DWT processing unit designed in Binary Number system. This project involves designing the first two-dimensional lifting-based DWT architecture in Residue Number System (RNS). The main purpose of designing this processing unit in RNS is due to its inherent properties such as modularity, parallelism and carry-free computation which enable faster computation speed. This report discusses the advantages of residue arithmetic, JPEG2000 Coding System, the implementation of the proposed RNS floating point arithmetic unit, design flow of proposed RNS 2-D Lifting-based DWT architecture, from RTL coding to synthesis of the design, and modelling of the proposed architecture using Matlab.