Wavelet denoising method based on adaptive threshold

Abstract

The invention discloses a wavelet denoising method based on an adaptive threshold. The wavelet denoising method comprises the following steps: (1) performing wavelet decomposition on a noise-contaminated signal to obtain wavelet coefficients of each layer and a highest-layer scale coefficient; (2) obtaining wavelet coefficient adaptive thresholds of all layers through iterative filtering; (3) extracting a pulse corresponding coefficient from each layer of wavelet coefficients by utilizing a chi-square energy window method; (4) setting a non-pulse corresponding coefficient in each layer of wavelet coefficient to zero to obtain a processed wavelet coefficient; and (5) performing reconstructing by using the processed wavelet coefficient of each layer and the scale coefficient of the highest layer to obtain a denoised signal.

Description

technical field [0001] The invention belongs to the technical field of signal processing, in particular to a wavelet denoising method based on an adaptive threshold. Background technique [0002] Wavelet threshold denoising is an effective Gaussian white noise suppression technology, which is widely used in the field of health status monitoring of people and things such as electrocardiogram detection and online monitoring of power equipment status. Threshold rules and threshold functions are the key problems in wavelet threshold denoising, which have a great impact on the denoising effect. [0003] In response to the above problems, scholars at home and abroad have proposed many solutions. Threshold rule methods include general threshold, unbiased risk threshold, and maximum and minimum threshold, etc., but there is a common problem of being affected by the length of the coefficient. Chinese Patent Publication No. CN105701456B, the publication date is October 25, 2019. The ...

AI Technical Summary

Problems solved by technology

[0004] The purpose of the present invention is to overcome the shortcomings and deficiencies existing in the existing wavelet threshold rules and threshold functions, and provide a wavelet denoising method based on adaptive thresholds in combination with the finite continuity of pulse signals and the statistical characteristics of Gaussian white noise to solve online monitoring, etc. The problem of threshold adaptive calculation and processing in the field, while effectively suppressing white noise, ensures the high fidelity of the pulse waveform after denoising

Images