摘要
给出了对称延拓方式下有限长信号不需逐级计算而直接得到小波系数的分解矩阵和由这些小波系数重构原信号的重构矩阵的构造方法,并给出了常用的相应于9/7小波的分解矩阵和重构矩阵及其基向量,它们可广泛用于基于小波的图像分块处理中。作为一种应用实例,将构造的小波变换矩阵用于FRIT图像去噪,不仅计算大大简化,而且相对于周期延拓的小波变换而言边界效应明显减少。
This paper proposes a new method to construct wavelets decomposing and reconstructing matrices of wavelet coefficients without iterative calculation in symmetrical extension for finite length signal, and correspondingly gives the base vectors and basis images of 9/7 wavelet. The matrices can be used for image partition processing based on wavelet method. As an example,the application of wavelet transform matrices constructed in this paper in FRIT image denoising will not only reduce the calculation greatly but also improve on the edge effect evidently compared with the periodic prolongation method.
出处
《光电子．激光》
EI
CAS
CSCD
北大核心
2007年第5期603-607,共5页
Journal of Optoelectronics·Laser
基金
国家自然科学基金资助项目(60302018)
