Age-dependent image processing method for face image

A face image and image processing technology, which is applied in the image field of face age changes, can solve the problem of unrealistic face images and achieve the effect of obvious aging characteristics

Inactive Publication Date: 2020-02-28
XI AN JIAOTONG UNIV
View PDF3 Cites 7 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] The object of the present invention is to provide a kind of image processing method that the face image changes with age, to overcome the problem that the existing method does not generate realistic face images with age

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
  • Age-dependent image processing method for face image
  • Age-dependent image processing method for face image
  • Age-dependent image processing method for face image

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0031] The present invention is described in further detail below in conjunction with accompanying drawing:

[0032] The flow chart of the concrete implementation of the present invention is as figure 1 As shown, the steps involved are as follows:

[0033] Step 1: Obtain a face image X and age tag information I corresponding to the face image;

[0034] Step 2: Extract the face image features of the face image X and encode the acquired face image features to obtain the hidden vector Z;

[0035] Face image features include face contour, eye size, nose size, and mouth size.

[0036] The representation feature hidden vector of the input face image X is Z, then:

[0037] Z=E(x)

[0038] The hidden vector Z includes the age label information and identity information of the face image, which are two important features that need to be guaranteed in the face age change generation task.

[0039] Step 3: Optimize the hidden vector Z to obtain the residual feature hidden vector, and ...

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 age-dependent image processing method for a face image. The method comprises the steps of obtaining the face image and age label information corresponding to the face image;optimizing an identity retention loss function through a feature extraction network; performing feature extraction on an input face image and a reconstructed face image by using an offline feature extractor; subtracting the input face image from the reconstructed face image; a vivid, vivid and close-to-reality face age change image can be generated by using the feature difference progressive residual network; through optimizing a loss function, particularly, optimizing an identity retention loss function, the difference between the feature maps extracted by the feature extractor is used to replace the direct difference between the input image and the final reconstructed image, the improvement enables the aging features of the generated face aging image sequence to be more obvious and closer to the real aging face, the method is simple, and the reconstructed face image is vivid.

Description

technical field [0001] The present invention relates to the field of human age change in computer vision, in particular to the feature difference progressive residual confrontation self-encoding network to obtain the image of human face age change. Background technique [0002] Face age change image generation is an interdisciplinary research problem across the fields of image processing, graphics, and computer vision. It realizes the generation of images of specific age groups of individuals. There are two main traditional methods: one is the method based on the face prototype, which first estimates the average image of the whole group in the predefined age group, and uses the difference between these average images to form an aging model; the other It is a method based on the physical model of the human face, using the quasi-hop number model to simulate the aging mechanism of the muscle, skin and skull of a specific individual. However, due to the lack of individual face ...

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): G06T3/00
CPCG06T3/0012G06T2207/20081G06T2207/20084G06T2207/30201
Inventor 魏平张雪香宋洁郑南宁
Owner XI AN JIAOTONG 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