Three-dimensional pulse wave image denoising method and system and storage medium

Abstract

The invention discloses a three-dimensional pulse wave image denoising method, a three-dimensional pulse wave image denoising system and a storage medium. The method comprises the following steps: acquiring three-dimensional pulse wave image data; when the frame number of the three-dimensional pulse wave images in a certain heartbeat period is smaller than a threshold value, interpolating each frame of image to enable the frame number of the three-dimensional pulse wave images in all heartbeat periods to be larger than or equal to the threshold value; decomposing the three-dimensional pulse wave image data after interpolation processing to obtain a low-rank matrix; and establishing a three-dimensional pulse wave image curved surface according to the low-rank matrix, and outputting a denoising result. The defect of image denoising of the three-dimensional pulse wave image can be overcome, and the denoising effect is improved.

Description

technical field [0001] The present invention relates to the technical field of image processing, in particular to a three-dimensional pulse wave image denoising method, system and storage medium. Background technique [0002] The effect of pulse signal preprocessing will directly affect the results of subsequent clinical analysis. Power disturbances, subtle wrist movements on the sensor, baseline drift due to breathing, and periodic deviations that may be due to chaotic phenomena all contribute to the noise of the pulse signal. If these noises are not removed, it will interfere with the subsequent analysis of the pulse signal. [0003] For three-dimensional pulse wave images, according to the schematic diagram of cutting pulse (such as figure 1 ) and matrix sensor diagram (such as figure 2 ), the signal is no longer only the pressure pulse waveform at a certain point in the radial artery, but a three-dimensional pulse image generated by multiple points in a certain area ...

AI Technical Summary

Problems solved by technology

However, in real application scenarios, the noise generated by the subject's breathing and movement often appears in multiple channels at the same time with the same regularity, and is mixed with the original signal, and sometimes even overwhelms the original signal

In this way, in the process of low-rank decomposition, RPCA will not be able to correctly distinguish the pulse wave signals of these channels and some regular noises, and it will be difficult to complete the work of signal extraction and interference removal

Images