Intelligent screening method and system thereof for abnormal tongue images
An abnormal tongue image and tongue image technology, applied in the intelligent screening method and system field of abnormal tongue image, can solve the problems affecting the accuracy of diagnosis results, the complexity of the self-state of the examinee, and the lack of objective and quantitative measurement Methods and other issues to achieve the effect of high accuracy, avoid limitations, and improve correctness
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0051] Such as figure 1 As shown, a kind of intelligent screening method of abnormal tongue image of the present invention comprises the following steps:
[0052] S1. Collect the data of abnormal tongue symptoms, conduct professional tongue evaluation on the collected tongue data according to the tongue and physical health status of different regions, ages, healthy or sub-healthy people, and construct the TCM tongue through the method of unanimous review diagnosis knowledge platform and expert-assisted diagnosis system;
[0053] Preferably, before proceeding to the next step, preprocessing and enhancement operations are performed on the input human tongue image. The specific steps are: use the mirror image of the human tongue image to convert the shape and color space, and use the image histogram to adjust the contrast of the human tongue image to enhance the contrast of the abnormal tongue symptom image in the human tongue image.
[0054] S2. Using the fine-grained image cl...
Embodiment 2
[0059] On the basis of Embodiment 1, this embodiment provides a process for extracting abnormal symptom features of an input human tongue image image by using a fine-grained image classification algorithm and an artificial neural network algorithm. Specific steps are as follows:
[0060] S101. Complete the training of the attention network model through the training set samples with category labels, label boxes, local area spatial positions and descriptions, and input human tongue image images with category labels, label boxes, local area spatial positions and descriptions for training A good attention network model generates a corresponding attention distribution map;
[0061] Further preferably, since in the traditional model training and testing process, it is necessary to perform scale transformation on the input human tongue image according to the network structure, in the transformation process, it is easy to cause local information loss and the candidate area still cont...
Embodiment 3
[0078] On the basis of Embodiment 1 or Embodiment 2, this embodiment provides an intelligent screening system for abnormal tongue images, which includes a server, a photographing device, a display unit, an intelligent terminal, and a recording unit; the server includes: abnormal tongue images Health check module, match module, information transfer module, recheck module and transfer module.
[0079] The photographing device is used to photograph the subject's abnormal tongue image, and transmits the characteristic photos of the subject's abnormal tongue image symptom to the server; further preferably, the photographing device is equipped with a model for displaying the tongue image to instruct the subject to take pictures. instruction module. In this embodiment, by installing an indication module in the photographing device, it is very convenient for users to take photographs, so that ordinary users without medical knowledge can also use it. The shooting device may be any one...
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