Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Face portrait synthesis method based on deep coupling self-coding

A face portrait and synthesis method technology, applied in the field of image processing, can solve problems such as insufficient training data

Inactive Publication Date: 2019-08-27
XIDIAN UNIV
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0008] The purpose of the present invention is to overcome the defects of the above-mentioned existing methods, and propose a face portrait synthesis method based on deep coupling self-encoding to solve the problem of insufficient training data and synthesize more accurate and realistic face portraits

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 portrait synthesis method based on deep coupling self-coding
  • Face portrait synthesis method based on deep coupling self-coding
  • Face portrait synthesis method based on deep coupling self-coding

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0047] The core idea of ​​the present invention is to synthesize face portraits based on deep coupling self-encoding. Deeply coupled autoencoder adds hidden training portraits with specific identity information as hidden data to insufficient original training data to provide sufficient training data with specific information. The specific implementation method is given below:

[0048] refer to figure 1 , the implementation steps of this embodiment are as follows:

[0049] Step 1, train the coupled self-editor to obtain the nonlinear mapping relationship between face photos and portraits.

[0050] Train the face photo coupled autoencoder and the face portrait autoencoder respectively, and then train the single-layer neural network constructed by the coupled autoencoder to establish the nonlinear mapping relationship between the face photo and the portrait:

[0051] 1a) In the face photo coupling autoencoder, the face photo x i As input, its output is a reconstructed face ph...

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 portrait synthesis method based on deep coupling self-coding, which mainly solves the problem that in the prior art, when the training data is insufficient, a synthesized face portrait lacks part of specific identity information. The implementation scheme comprises respectively training a face photo coupling auto-encoder, a face portrait coupling auto-encoder and a single-layer neural network formed by the coupling auto-encoders, using the single-layer neural network to find a non-linear mapping relation between the face photo and the face portrait, putting the face photo into the trained coupling auto-encoder to generate a hidden training photo block with specific information, representing the test photo candidate block set by a training photo block and a weight matrix in a linear combination manner, obtaining a face portrait candidate block set through the similarity hypothesis, and fusing the human face components in the human face portrait candidate block set to form a human face portrait. According to the invention, the synthesized face portrait has more specific information, is cleaner and more realistic, and can be used for converting a figurephoto into a figure portrait in digital entertainment.

Description

technical field [0001] The invention belongs to the technical field of image processing, and further relates to a method for synthesizing human face portraits, which can be used in digital entertainment to convert photos of people into portraits of people. Background technique [0002] Nowadays, science and technology are more and more used in our daily life. Photo processing software can perform various processing on photos: adding filters, beautifying, changing the background and so on. These are realized through a series of digital image processing techniques, such as face recognition, smoothing filtering, etc. When converting face photos into portrait pictures, some details such as glasses and hairpins will always be lost. Only when we prepare sufficient training data can we synthesize realistic facial portraits. [0003] In view of the above problems, the prior art methods mainly try to use three ways to solve the problem of insufficient training data. The first and...

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): G06K9/00G06K9/62G06N3/04
CPCG06N3/04G06V40/16G06F18/214
Inventor 张铭津吴芊芊郭杰李云松刘凯
Owner XIDIAN UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com