图像小波分解的FPGA实现  

FPGA Implementation of the 2-D Discrete Wavelet Transform

作　　者：黄本雄[1] 段善维[1] 胡海[1] 

机构地区：[1]华中科技大学电子与信息工程系,湖北武汉430074

出　　处：《计算机工程与科学》2005年第3期32-34,60,共4页Computer Engineering & Science

摘　　要：小波分析作为信号处理领域中的一种重要方法,在信号处理、模式分析和图像处理等方面得到了广泛的应用。然而小波变换巨大的运算量却使得它在实时处理领域中的应用受到了限制。本文根据离散小波变换的 Mallat算法,提出了一种FPGA实现高速小波分解的方法,设计出的小波变换模块结构清晰而且规则,易于级联,可实现多级变换。同时,运算精度和处理速度均满足实时图像处理的要求。Wavelet transform has been widely used in signal processing, pattern analysis and image processing. However, its large computational complexity limits its practical usage in real time systems. According to the Mallat algorithm, the paper proposes an implementation of the fast 2 D discrete wavelet transform (DWT) based on the FPGA technology. The basic module designed for the one scale 2 D DWT has a clear and regular architecture, which facilitates the assembling of the basic modules to implement the multi scale 2 D DWT. The accuracy and speed of our system meet the requirements of real time image processing.

关 键 词：图像处理 小波分解 FPGA 信号处理 MALLAT算法 离散小波变换 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术] TN911.73[自动化与计算机技术—计算机科学与技术]