首页 | 官方网站   微博 | 高级检索  
     

9/7提升小波变换图像处理算法的高速FPGA实现
引用本文:王巍,杜治芸,曾勇,唐政维,李凯,李博.9/7提升小波变换图像处理算法的高速FPGA实现[J].微电子学,2009,39(6).
作者姓名:王巍  杜治芸  曾勇  唐政维  李凯  李博
作者单位:重庆邮电大学,光电工程学院,重庆,400065
摘    要:提升结构(Lifting Scheme)是一种新的双正交小波变换构造方法.这种方法使得计算复杂度大大降低,有效地减少了运行时间.介绍了基于FPGA的高速9/7提升小波变换的设计,提出采用多级流水线硬件结构实现一维离散小波变换(1-D DWT).该结构使系统吞吐量提高到原来的3倍,面积仅增加40%.在实现二维离散小波变换(2-D DWT)时采用基于行的结构,可以提高片内资源利用率和运行速度,满足小波变换实时性的要求.

关 键 词:离散小波变换  提升结构  图像处理

High-Speed FPGA Implementation of 9/7 Lifting-Based DWT Image Processing Algorithms
WANG Wei,DU Zhiyun,ZENG Yong,TANG Zhengwei,LI Kai,LI Bo.High-Speed FPGA Implementation of 9/7 Lifting-Based DWT Image Processing Algorithms[J].Microelectronics,2009,39(6).
Authors:WANG Wei  DU Zhiyun  ZENG Yong  TANG Zhengwei  LI Kai  LI Bo
Abstract:Lifting scheme is a new method for biorthogonal discrete wavelet transform (DWT), which greatly reduces the computational complexity.In this paper, an FPGA-based high-speed 9/7 lifting DWT algorithm was presented.Using multi-stage pipelining structure, one-dimensional discrete wavelet transform (1-D DWT) was realized to improve system throughput by 3 times, with only 40% increase in size.A line-based architecture was applied to realize 2-D DWT, which features better performance in terms of throughput rate and hardware utilization.
Keywords:FPGA  Discrete wavelet transform(DWT)  Lifting scheme  Image processing  FPGA
本文献已被 万方数据 等数据库收录!
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司    京ICP备09084417号-23

京公网安备 11010802026262号