Vein imaging recognition method based on the combination of infrared image and Doppler ultrasound

Abstract

The vein imaging recognition method based on the combination of infrared image and Doppler ultrasound provided by the present invention includes: acquiring the vein image of the patient to be identified, and preprocessing the vein image; the vein image includes: infrared medical image and The corresponding ultrasonic Doppler blood flow spectrogram; identifying the characteristic value points of the infrared medical image and the ultrasonic Doppler blood flow spectrogram, and performing pixel point matching; The pixels in the medical image are slided pixel by pixel, and the local contrast of the infrared image of each pixel is calculated; the local contrast of the infrared image and the local contrast of the spectrogram are combined to obtain the weighted local contrast of each pixel, Then the weighted local contrast map of the whole image is obtained; the target can be extracted by performing threshold segmentation on the weighted local contrast map, and then the development and recognition of vein images can be realized.

Description

technical field [0001] The invention relates to the field of medical image processing, in particular to a vein development recognition method based on the combination of infrared images and ultrasonic Doppler. Background technique [0002] Infrared imaging of veins plays an important role in medical assistance and biometric identification. In terms of medical treatment, venous imaging technology has been developed rapidly. According to relevant data, the success rate of normal adult venipuncture for the first time is 73%; the failure rate of the first two venipuncture for children is 58%; Generally speaking, the probability of "missing the needle" during venipuncture is 23-28%. Since there are many superficial subcutaneous tissues in the human body, it will be affected during the venipuncture process, such as: blood vessel depth, fat layer thickness, skin pigment content, etc. Affected by many factors, inexperienced or even experienced medical staff tend to have a low succe...

AI Technical Summary

Problems solved by technology

[0005] The invention application with the application number 201610980034.0 discloses a device and method for three-dimensional reconstruction of human superficial veins based on binocular stereo vision. The near-infrared light source and the camera are respectively placed on both sides of the acquisition object, effectively avoiding the skin surface structure and texture. The reflection of the light source can improve the imaging quality, but the fusion process of near-infrared light source and camera imaging is not easy to calibrate, and the calculation process is complicated, which increases the difficulty of implementation

[0006] The invention application with the application number of 201811642253.3 discloses a method and equipment for obtaining finger vein image enhancement. A low-cost camera can obtain the finger vein image of the finger irradiated with near-infrared rays. After obtaining the finger vein image, pass the two-dimensional symmetrical mask matrix The low and low frequency matrix coefficients of discrete wavelet transform pre-process the finger vein image, and obtain the finger vein texture feature by detecting the valley points of the processed finger vein image, which can identify the position of the vein image, but cannot perform 3D reconstruction of the vein image

Images