Face image correction method based on decoupling expression learning generative adversarial network

A face image and network technology, applied in the field of face image conversion, to achieve the effect of fast convergence, good effect, and strong generalization ability

Inactive Publication Date: 2020-07-17
天津中科智能识别有限公司
View PDF2 Cites 15 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the face conversion problem is still challenging, because this is a typical pathological problem, that is, given a profile face image, there may be multiple corresponding frontal face images

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 image correction method based on decoupling expression learning generative adversarial network
  • Face image correction method based on decoupling expression learning generative adversarial network
  • Face image correction method based on decoupling expression learning generative adversarial network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0045] The present invention will be described in further detail below in conjunction with the accompanying drawings and specific embodiments. It should be understood that the specific embodiments described here are only used to explain the present invention, not to limit the present invention.

[0046] The present invention learns a set of highly complex non-linear transformations through a face image conversion method based on decoupling expression learning generative confrontation network, which is used to transform the pose of the face image into an angle while maintaining a good texture and identity traits.

[0047] Such as figure 1As shown, the face image correction method based on decoupled expression learning generative confrontation network, including steps:

[0048] In step S1, preprocessing is performed on the face images in the Multi-PIE face dataset.

[0049] First, the original high-resolution face image is cropped in a unified alignment and cropping method, a...

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 image correction method based on a decoupling expression learning generative adversarial network. The method comprises the following steps: a model comprising an auto-encoder of a U-net network structure and three discriminators is trained; then, identity information representation of the face image is learned through the auto-encoder, the posture of the face image can be generated through explicit control in combination with the posture hidden code, and the three discriminators predict authenticity, posture and identity information of the face image respectively, so that the face image with rich texture details is generated. According to the invention, the visual quality of the generated face image can be significantly improved.

Description

technical field [0001] The invention relates to the technical field of rectification of human face images, in particular to a face image rectification method based on decoupling expression learning to generate an adversarial network. Background technique [0002] The face image conversion task actually serves face recognition. In recent years, face recognition based on deep learning methods has made great progress. However, when the face recognition model trained on the frontal face image dataset is detected on the profile face image, the performance of the model will be severely degraded. This shows that in face recognition, the pose variation of faces is still a challenge and deserves further research. Therefore, in order to improve the accuracy of the face recognition model, the face image conversion method is naturally introduced. As the name implies, the face image normalization task refers to inferring the corresponding frontal face image from a given profile face i...

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): G06K9/00G06N3/04G06N3/08
CPCG06N3/08G06V40/161G06N3/045
Inventor 马鑫侯峦轩赫然孙哲南
Owner 天津中科智能识别有限公司
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