A method and system for face complexion analysis based on deep learning

A technology of deep learning and analysis methods, applied in the field of facial skin color analysis based on deep learning, can solve problems such as insufficient meeting demand, and achieve the effect of protecting privacy

Active Publication Date: 2022-04-01
NANJING UNIV OF POSTS & TELECOMM
View PDF2 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Although there are some simple measuring instruments such as heartbeat and blood pressure at home that can reflect the health status of the body to a certain extent, they are far from enough to meet the needs. We need more tools and use more common methods to let people Have a clear understanding of your own health

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
  • A method and system for face complexion analysis based on deep learning
  • A method and system for face complexion analysis based on deep learning
  • A method and system for face complexion analysis based on deep learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0040] The present invention will be further described below in conjunction with the accompanying drawings. The following examples are only used to illustrate the technical solution of the present invention more clearly, but not to limit the protection scope of the present invention.

[0041] A kind of human face skin color analysis method based on deep learning of the present invention, see figure 1 shown, including the following steps:

[0042] In step S1, a face image is acquired, and a corresponding user identity is identified based on the face image.

[0043] Identifying the corresponding personal identity based on the face image is the process of identity verification, see figure 2 As shown, the specific process of identity verification based on the face image is:

[0044] (1) Establish a user feature library: collect user face images, extract face feature vectors from the face images, and save the face feature vectors and corresponding user identities to form a user...

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 method and system for analyzing human face and facial skin color based on deep learning, including: step S1, acquiring a face image, and identifying the corresponding user identity according to the face image; step S2, extracting the cheek according to the face image , lips, and eye color feature vectors; step S3, segment the image containing the tongue from the face image, and extract the color feature vectors of the tongue coating and coating quality from the tongue image; step S4, establish the user identity and its corresponding The correspondence between the color feature vectors of cheeks, lips, eyes, tongue coating, and tongue body forms a skin color feature library. The invention utilizes the face recognition technology for identity verification, analyzes the skin color of the face and tongue, and establishes a color feature database of the face, so as to prepare for knowing the health conditions of the human body in time.

Description

technical field [0001] The present invention relates to the technical field of image and video analysis, in particular to a method for analyzing human face and facial skin color based on deep learning. Background technique [0002] With the development of the country's economy, people's living standards are gradually improving, and at the same time they are paying more attention to personal health. However, due to the lack of medical knowledge, they cannot respond to the diseases that appear in the body in a timely manner, which leads to the deterioration of the disease and many irreparable losses. [0003] With the development of society, people's pressure is also increasing. Some traffic safety situations such as sudden overtime death or overtired driving often occur, causing great losses to society and families. In fact, before the outbreak of many diseases, there will be many symptoms, which will appear on the face and other places. If they can be detected in time, there...

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 Patents(China)
IPC IPC(8): G06V40/16G06V10/74G06V10/766G06V10/82G06V10/40G06F21/32G16H50/20
CPCG06F21/32G16H50/20G06V40/162G06V40/168G06F18/22
Inventor 李晓飞李联炜吴聪柴磊
Owner NANJING UNIV OF POSTS & TELECOMM
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