Construction method of detection model for facial motion retardation based on geometrical characteristics and textural characteristics

A technology of texture features and geometric features, applied in the field of detection model construction

Active Publication Date: 2020-06-19
ZHEJIANG UNIV
View PDF9 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The research by Andrea Bandini and M.Rajnoha et al. has confirmed through experiments that the expression loss of PD patients can be recognized to a certain extent, but the accuracy of recognition needs to be further improved.

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
  • Construction method of detection model for facial motion retardation based on geometrical characteristics and textural characteristics
  • Construction method of detection model for facial motion retardation based on geometrical characteristics and textural characteristics
  • Construction method of detection model for facial motion retardation based on geometrical characteristics and textural characteristics

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0053] Such as figure 1 As shown, it is an overall frame diagram of the detection model of facial slow motion based on geometric features and texture features in the method of the present invention. HOG-XY: The image sequence is represented by the spatial axis X, Y and the time axis T, where the HOG feature of the texture feature in the XY plane is called HOG-XY; HOG-XT: the image sequence uses the spatial axis X, Y and time Axis T, wherein the HOG feature of the texture feature in the XT plane is called HOG-XT; HOG-YT: the image sequence is represented by the spatial axis X, Y and time axis T, and the HOG feature of the texture feature in the YT plane The feature is called HOG-YT; PCA: Principal Component Analysis, principal component analysis dimensionality reduction method. KNN: k-NearestNeighbor, k nearest neighbor classification algorithm. SVM: SupportVector Machine, support vector machine. PD patients: Parkinsondisease patients, Parkinson patients. HC object: Healthy...

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 a construction method of a detection model for facial motion retardation based on geometrical characteristics and textural characteristics. The constructed detection model based on facial expression characteristics can be used for detecting motion retardation symptoms related to Parkinson's disease. The facial expression features include geometrical features and textural features. The geometry defines FEF (facial expression factor) and FECF (facial expression change factor) to quantify facial expressions of the static image. However, these geometric features relate onlyto spatial information, where SEM facial features are constructed with reference to Principal analysis. And the textural features use an extended HOG algorithm to extract dynamic expression changes in a short time. The texture features are combined with the spatial dimension and the time dimension, so that the defects of geometric features are overcome; finally, a detection model based on facialexpression features is constructed by using five supervised machine learning methods. Experimental results show that the F1 index of the system can reach up to 94.46%.

Description

technical field [0001] The invention relates to the technical field of detecting facial slowness of Parkinson's patients based on facial video, in particular to a method for constructing a detection model of facial slowness based on geometric features and texture features. Background technique [0002] As we all know, Parkinson's is one of the typical chronic diseases of the elderly, and the incidence rate of the elderly over 65 years old can reach 1% to 2%, which is more than three times the incidence rate of all humans (0.3%). For most Parkinson's patients (PD patients), Parkinson's motor symptoms are typical, mainly manifested in four aspects: resting tremor, muscle rigidity, bradykinesia and postural balance disorder. Around these four aspects, the new version of the World Movement Disorder Society Parkinson's Disease Comprehensive Rating Scale (MDS-UPDRS) detects motor symptoms through facial expressions, limb rotations, finger movements, palm movements, toe movements, ...

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
IPC IPC(8): G06K9/62G06K9/00G06N20/00
CPCG06N20/00G06V40/165G06V40/171G06F18/253
Inventor 苏鸽尹建伟林博罗巍
Owner ZHEJIANG UNIV
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