提升小波变换的三种算法性能比较

离散小波变换(DWT)在语音,图像等信号处理中有着广泛的应用,在JPEG2000标准中就推荐采用5/3和9/7小波来分别进行无损和有损图像压缩,取代基于DCT变换的图像压缩,并且还推荐采用提升方法来实现。提出三种基于提升方法的二维离散小波变换的并行算法,并在超常超标量数字指令(VLIW)的数字信号处理器(DSP)上进行了性能方面的比较。这里,我们以在图像压缩中常用的不同分辨率的图像作为实验对象。实验结果表明,此三种算法对图像数据进行小波变换的处理时间有了明显缩短,并且实现在参数空间的不同点上都得到更好的效果。

Performance Comparison of Three Arithmetic of Lifting Wavelet Transform

Dimensional discrete wavelet transform(DWT) is becoming one of the standard tools for audio and image signal processor,the 5/3 and 9/7 filter-pairs included in JPEG-2000 was considered for lossless and lossy image compression,instead of based on DCT image compression and improved using lifting scheme.This paper proposes three arithmetic based on lifting scheme of two-dimensional discrete wavelet transform(2D DWT) and compare with respect to their performance on a very long instruction-word(VLIW) digital signal processor(DSP).Here,we choose various image sizes usually using in compression.The experimental results show that each realization can reduce the amount of time requirement and performs better for different points of the parameter space.