Rhonchus identification method based on frequency domain image processing

A recognition method and technology of dry rales, applied in speech analysis, instruments, etc., can solve problems such as being easily affected by the external environment

Inactive Publication Date: 2016-04-13

HANGZHOU BESTPLUS INFORMATION TECH CO LTD

9 Cites 4 Cited by

AI-Extracted Technical Summary

Problems solved by technology

[0002] Rales are an important abnormal breath sound. By detecting the moment, number, and distribution of rales, doctors can judge the relevant information of lung diseases in ...

Method used

[0052] Use median filtering and subtract the result from the original spectrogram, this method can enhance the contrast between pixels in the image, make the color difference in different regions more obvious...

Abstract

The invention relates to a rhonchus identification method based on frequency domain image processing. The method is characterized in that audio signals are converted from time domain into frequency domain through fast Fourier transform, the produced frequency domain images is subjected to binarization processing by the aid of a preset threshold, and specific rhonchus signals are obtained through filtering. The rhonchus identification method has the advantages that rhonchus can be identified fast, the method is high in efficiency, low in calculation amount, low in system load and simple in maintenance, and the blank that currently breath sounds cannot be automatically identified is filled up; by the efficient calculation ability of a computer, the tiny audio frequency which cannot be heard by human ears can be detected, and controversial rhonchus types can be categorized according to specific numerical values.

Application Domain

Speech analysis

Technology Topic

Fft fast fourier transformFrequency domain +9

Image

Examples

Experimental program(1)

Example Embodiment

[0033] Example: such as figure 1 As shown, a rale recognition method based on frequency domain image processing, including audio preprocessing, binarized frequency domain image generation, and feature extraction of dry rales; the whole method can be realized based on computer mathematical calculation software MATLAB.

[0034] The audio preprocessing operation flow includes the following steps:

[0035] 1) Read the audio file locally, and store the audio data in the memory in the form of a floating-point array;

[0036] There is a related audio reading function wavread in MATLAB, which can read audio files in wav format and convert the corresponding data into matrix arrays and store them in memory.

[0037] 2) Use high-pass filtering to filter out some external noise during recording;

[0038] 3) Use low-pass filtering to filter out the noise generated by folding distortion;

[0039] Due to the particularity of breath sound files, only any one of the two channels can be used. Select the Butterworth filter to perform band-pass filtering on the sound wave, and filter out sounds other than 60Hz-2000Hz. Usually, the external noise generated by clothing friction and body shaking is lower than 60Hz. Therefore, pure breathing sounds can be effectively extracted through filtering to reduce the impact of external interference on the detection results.

[0040] 4) Normalize the data and remove the linear trend;

PUM

Description & Claims & Application Information

We can also present the details of the Description, Claims and Application information to help users get a comprehensive understanding of the technical details of the patent, such as background art, summary of invention, brief description of drawings, description of embodiments, and other original content. On the other hand, users can also determine the specific scope of protection of the technology through the list of claims; as well as understand the changes in the life cycle of the technology with the presentation of the patent timeline. Login to view more.