Face age synthesis method for weak label data

A technology of tagging data and tags, which is applied in the field of computer science and technology artificial intelligence, can solve problems such as poor picture quality, lack of large amounts of data, ghosting of face images, etc., to achieve strong robustness, solve data scarcity, and strong robustness Effect

Pending Publication Date: 2021-03-12
NANJING UNIV OF INFORMATION SCI & TECH
View PDF6 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Due to the lack of a large amount of data in this method, it is easy to cau

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 age synthesis method for weak label data
  • Face age synthesis method for weak label data
  • Face age synthesis method for weak label data

Examples

Experimental program
Comparison scheme
Effect test

specific Embodiment

[0075] The present invention can be applied to the general public, such as: using a picture of an ordinary person to generate pictures corresponding to different age groups, such as Figure 4 As shown, it is the contrast effect between the generated picture and the real result; this method solves the problem of data set scarcity in the face age synthesis task, and the synthesis retains most of the personal identity information, and the effect is good.

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 face age synthesis method for weak label data. The method belongs to the field of computer science and technology artificial intelligence, and comprises the specific steps ofhuman face feature extraction, human face age synthesis and identity information enhancement. According to the method, the problems of inaccurate data set labels and lack of matching age group face pictures can be solved, and meanwhile, more personal facial feature information is reserved due to the addition of the loop network, so that the generated regression/aging face effect is better; in addition, a good generation effect can still be ensured on the basis of solving the problem of insufficient data sets; the problem of data scarcity in a traditional face age synthesis task is solved, andthe method is widely applied to real life, such as missing population searching, movie and television entertainment, public welfare project propaganda and the like.

Description

technical field [0001] The invention belongs to the field of computer science and technology artificial intelligence, and in particular relates to an age synthesis method, in particular to a face age synthesis method for weak label data. Background technique [0002] Face synthesis is a technology to study someone's past and future appearance. This technology has a wide range of applications in real life, such as finding missing persons, publicizing public welfare projects in film and television entertainment, etc. In recent years, many scientists have devoted themselves to this work, but due to the scarcity of data, the research in this field is always facing great challenges. How to solve this problem is a direction worthy of further study. Traditional face synthesis methods can be divided into physical modeling and prototype generation methods. Physical modeling uses formulas to calculate the changes in the face's skull, face shape, skin, and facial features at different...

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
CPCG06N3/08G06V40/178G06V40/168G06N3/045G06F18/2155
Inventor 周媛马莞悦何军
Owner NANJING UNIV OF INFORMATION SCI & TECH
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