Face skin type analysis method and system based on depth learning and generation confrontation network

A technology of deep learning and analysis method, applied in the field of face skin quality analysis, can solve the problems of limited effect and difficult data acquisition, and achieve the effect of good training effect

Inactive Publication Date: 2017-12-05
EMOTIBOT TECH LTD
View PDF4 Cites 20 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] However, the current research on face analysis seldom analyzes skin details. Because face and skin data are relatively private and involve medical behavior, the data is not easy to obtain. In the past, traditional i

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
  • Face skin type analysis method and system based on depth learning and generation confrontation network
  • Face skin type analysis method and system based on depth learning and generation confrontation network
  • Face skin type analysis method and system based on depth learning and generation confrontation network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0035] With the development of mobile apps and the Internet, numerous image editing and live broadcast applications have emerged. Most of the current applications use image filters or textures to beautify the screen, and very few applications analyze and optimize human face skin. Therefore, the present invention will be based on the computer vision algorithm to analyze the details of human face skin (such as acne, wrinkles, moles, enlarged pores, shiny skin, dry skin, dark circles, etc.).

[0036] The beauty assistant is also a popular project in the artificial intelligence industry at present, but the application of the beauty assistant in life is often not just needed. For women, most women spend tens of minutes every day in front of the mirror or through the camera of mobile devices to organize their appearance. commercial application. For this reason, the present invention designs an intelligent assistant for beauty makeup by integrating the intelligent assistant for bea...

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 provides a face skin type analysis method and system based on depth learning and the generation confrontation network. The method comprises steps that the image acquisition step, a to-be-analyzed face image is acquired; the block division step, the to-be-analyzed face image is analyzed, and skin blocks of the to-be-analyzed face image are divided according to organs; the analysis step, different skin analyzers are inputted to different skin blocks and are used for analyzing skin states of the corresponding skin blocks; and the result output step, the analysis results of all the skin analyzers are outputted. The method is advantaged in that on the condition that face skin type data is not easy to acquire and distribution is free, through the generation confrontation network, auxiliary data is generated, a depth learning model is utilized to replace a traditional image processing algorithm for skin type analysis application, face skin details can be analyzed, in combination with the generation confrontation network, for different-characteristic skins, the limited data is utilized to generate training data, and the better training effect is acquired.

Description

technical field [0001] The invention belongs to the technical field of image processing, and in particular relates to a face and skin quality analysis method and system based on deep learning and generative confrontation networks. Background technique [0002] In the past few decades, there have been many related researches on deep learning, but due to the huge amount of training data required, many of them cannot be realized. In recent years, due to the development of big data and the Internet, researchers can obtain a large amount of training data, so deep learning technology has begun to develop rapidly. With the popularity of live broadcasts and short videos, commercial applications of facial effects and editing have received a lot of attention and research data. [0003] However, the current research on face analysis seldom analyzes skin details. Because face and skin data are relatively private and involve medical behavior, the data is not easy to obtain. In the past,...

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): G06K9/00G06K9/62G06N3/04G06N3/08
CPCG06N3/08G06V40/171G06V40/172G06V40/161G06N3/045G06F18/241
Inventor 简仁贤张惠棠杨闵淳
Owner EMOTIBOT TECH 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