Hypertension risk prediction method based on traditional Chinese medicine theory and palm multi-feature extraction
A technology for risk prediction and hypertension, applied in the field of medical image processing, which can solve the problems of cumbersome and inconvenient detection
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0087] figure 1 It is a schematic flowchart of a hypertension risk prediction method based on TCM theory and palm multi-feature extraction provided by Embodiment 1 of the present invention; figure 2 It is a schematic structural diagram of the key point model of the hand in Embodiment 1 of the present invention; figure 1 , figure 2 As shown, a hypertension risk prediction method based on TCM theory and palm multi-feature extraction includes:
[0088] S10, acquiring an image of the palm to be tested;
[0089] S20, establishing a key point model of the hand; the key point model of the hand includes: position information of main joints of the hand;
[0090] S30, performing corresponding ROI segmentation on the image information according to the features of the lifeline crossing the midline, the ruddy feature, the uplift feature, and the hypertrophy feature;
[0091] S40, detect the lifeline crossing the midline ROI region corresponding to the lifeline crossing the midline fe...
Embodiment 2
[0119] Figure 8 It is a schematic flow diagram of detecting the lifeline crossing the midline ROI region corresponding to the lifeline crossing the midline feature in the second embodiment; as Figure 8 As shown, on the basis of Embodiment 1, a hypertension risk prediction method based on TCM theory and palm multi-feature extraction, the step S40 is to detect the lifeline crossing midline ROI region corresponding to the lifeline crossing midline feature, and based on Edge detection algorithm and curve fitting algorithm judge whether the lifeline crosses the midline, if the lifeline intersects the midline, calculate the weight Weight 1 , otherwise the weight is 0, including:
[0120] S401. Perform grayscale processing on the image in the ROI region where the lifeline crosses the midline, and convert it into a grayscale image; the conversion formula is: Gray=(R*30+G*59+B*11+50) / 100.
[0121] S402, after obtaining the gradient in the x direction through the Scharr operator, us...
Embodiment 3
[0154] Figure 11 It is a schematic flow diagram of performing ruddy detection on the ruddy ROI region corresponding to the ruddy feature in the third embodiment; Figure 12 It is the effect diagram of color area extraction in the third embodiment; as Figure 11 , Figure 12 As shown, on the basis of Embodiment 1, a method for predicting the risk of hypertension based on TCM theory and palm multi-feature extraction, the step S50, the rosy ROI area corresponding to the ruddy feature is ruddy detection, by HSV-based The color gamut space judges whether it is ruddy, and if it is ruddy, the weight of ruddy is Weight 2 , otherwise the weight is 0, including:
[0155] S501, convert the acquired image into HSV color space; HSV can more intuitively observe the hue, vividness and lightness of the color, so it performs better in color contrast, and it is easier to track objects of a certain color, which can be used to segment specific Color object; the calculation formula of RGB to ...
PUM
Abstract
Description
Claims
Application Information
- R&D Engineer
- R&D Manager
- IP Professional
- Industry Leading Data Capabilities
- Powerful AI technology
- Patent DNA Extraction
Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.
© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com