摘要
本文首先阐明了子波变换理论利用可变时域和频域分辨特性表达信号、获取信号特征的原理，提出了利用神经网络计算方法计算子波变换系数的新方法，并讨论了与人视觉系统密切相关的子波变换神经元的特性，提供了计算机仿真子波变换信号的结果。理论分析和实验结果表明，子波变换不仅具有对信号多分辨表达的特性，而且可以有效地压缩被处理信号。
Clarified the rationale that wavelet transform represents a signal with varying frequency and spatial resolution and thus captures the essence of a signal,a kide of neural network computation for finding out the projection coefficients of wavelets is proposed. Different wavelet transform neurons which closely match the human vision system ate discussed.The results of several experimental simulation of wavelet transforms are presented.Theoritical analysis and experimental results show a usefulness of neural network for computing wavelet transform which,besides multi resolution reptesentation,also effectively compresses data dimension of signals.
出处
《四川轻化工学院学报》
1995年第2期1-9,共9页
Journal of Sichuan Institute of Light Industry and Chemical Technology
关键词
神经网络
子波变换
信号处理
计算
仿真
neural networks
wavelet transforms
signal approximation
