Accurate facial paralysis degree evaluation method and device based on 3D point cloud segmentation

An evaluation method and point cloud technology, applied in neural learning methods, acquisition/recognition of facial features, instruments, etc., can solve problems such as large errors and low evaluation efficiency

Pending Publication Date: 2020-11-27
SHENZHEN DJ INNOVATION IND CO LTD
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] In order to solve the technical problems of large errors and low evaluation efficiency in the existing facial paralysis degree evaluation method, the present invention provides a precise facial paralysis degree evaluation method and device based on 3D point cloud segmentation

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Accurate facial paralysis degree evaluation method and device based on 3D point cloud segmentation
  • Accurate facial paralysis degree evaluation method and device based on 3D point cloud segmentation
  • Accurate facial paralysis degree evaluation method and device based on 3D point cloud segmentation

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0064] see figure 1 , the present embodiment provides a method for evaluating the degree of facial paralysis based on 3D point cloud segmentation. Extensive industrial application, for example, it can be used as an independent program in the mobile terminal and client terminal, which can be used for correction and inspection of patients with facial paralysis during the non-treatment period, and can also be used as a preventive method for patients without facial paralysis. Wherein, the method for evaluating the degree of accurate facial paralysis includes the following steps, namely steps (1)-(3).

[0065] Step (1): Establish a 3D semantic segmentation model for facial paralysis. In this embodiment, the method for establishing a 3D semantic segmentation model of facial paralysis includes the following steps, namely steps (1.1)-(1.4). see figure 2 , in the facial paralysis 3D semantic segmentation model, in the facial paralysis 3D semantic segmentation model, the two eyebrow...

Embodiment 2

[0091] This embodiment provides a method for accurately evaluating the degree of facial paralysis based on 3D point cloud segmentation, which is similar to that of Embodiment 1, except that the three-dimensional deep network model of this embodiment is different. The specific structure of the three-dimensional deep network model of the present embodiment can be designed separately according to the specific requirements of the user, and can directly use the standard PointNet model structure or modify the structure according to the specific requirements of the user. A specific training parameter of the model is as follows: Use Gaussian distribution random numbers to initialize the ownership value and threshold of the deep full convolutional network model. The learning rate is initialized to 0.001, the model target Loss threshold is 0.1, the maximum training times of the model is set to 20000, the optimizer algorithm is Adam, and the loss function is Binary CrossEntropy. .

Embodiment 3

[0093] This embodiment provides a device for evaluating the degree of accurate facial paralysis based on 3D point cloud segmentation. The device applies the method for evaluating the degree of accurate facial paralysis based on 3D point cloud segmentation in Embodiment 1 or Embodiment 2. Among them, the precise facial paralysis degree evaluation device includes a detection model building module, a data acquisition module, a data processing module and a facial paralysis comprehensive evaluation module. The data acquisition module and the data processing module can form a data acquisition and processing module to be detected. These modules can be used as computer program modules or hardware modules, which can execute the relevant steps described in Embodiment 1 or Embodiment 2.

[0094] The detection model building module is used to build a 3D semantic segmentation model for facial paralysis, which is actually used to implement step (1) in Embodiment 1. In the facial paralysis 3...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention discloses an accurate facial paralysis degree evaluation method and device based on 3D point cloud segmentation. The method comprises the following steps: establishing a facial paralysis3D semantic segmentation model; acquiring to-be-detected data and processing the to-be-detected data; sequentially inputting an expression-free natural state static image, a sequence image I, a sequence image II, a sequence image III and a sequence image IV into the facial paralysis 3D semantic segmentation model to output a plurality of corresponding groups of face shapes, and updating the plurality of groups of face shapes; evaluating the facial paralysis degree of a user to be detected; calculating theta 1, theta 2, theta 3, theta 4, theta 5, theta 6, theta 7, theta 8, theta 9, theta 10, theta 11, |theta 12|, a1, a2, b1 and b2 and comparing the above values with threshold values thereof; and judging the facial paralysis degree of the user to be detected, and calculating a facial paralysis index. According to the invention, the detection model has high detection positioning precision, the precision and accuracy of the comprehensive evaluation and detection of the facial paralysis degree of the user to be detected are greatly improved, and a powerful support is provided for the prevention, discovery and treatment of facial paralysis patients.

Description

technical field [0001] The present invention relates to a method for evaluating the degree of accurate facial paralysis in the technical field of facial paralysis recognition, in particular to a method for evaluating the degree of accurate facial paralysis based on 3D point cloud segmentation, and also to a device for evaluating the degree of accurate facial paralysis based on 3D point cloud segmentation using the method. Background technique [0002] Facial paralysis is a common disease in which the motor function of facial muscles is hindered. Patients often have difficulty in completing basic facial movements such as closing eyes, raising eyebrows, puffing cheeks, wrinkling nose or opening mouth, and it is an area with a high incidence in my country. Facial paralysis is generally called facial paralysis. The general symptom is that the mouth and eyes are crooked. Patients often cannot even complete the most basic movements such as raising eyebrows, closing eyes, and puffin...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
Patent Type & Authority Applications(China)
IPC IPC(8): G06K9/00G06N3/04G06N3/08
CPCG06N3/084G06V40/165G06V40/171G06V40/174G06V40/172G06N3/045
Inventor 冯少华李伟中李健金波邓利平冼上轩
Owner SHENZHEN DJ INNOVATION IND CO LTD
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap