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

Video face changing method and device

A video and face detection technology, applied in the field of video processing, can solve problems such as high cost of face replacement, threats to user privacy, light, poor skin color processing, etc., and achieve the effect of optimizing the shape of facial features

Pending Publication Date: 2021-06-11
GUANGZHOU JIUBANG DIGITAL TECH
View PDF0 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] Face-changing based on deep learning requires users to upload images and videos to the server for processing. From a technical perspective, developers of the above user data can use them at will, and pose a great threat to users' personal privacy, and the cost of face-changing is high; while local The realized lightweight face change does not deal well with light, skin color, etc., and the traces of face change are obvious. When the shape of the facial features changes, it cannot be adjusted well

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
  • Video face changing method and device
  • Video face changing method and device
  • Video face changing method and device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0066] In order to make the object, technical solution and points of the present invention clearer, the present invention will be further explained below in conjunction with the accompanying drawings. All other embodiments obtained by persons of ordinary skill in the art without creative efforts belong to the protection scope of the embodiments of the present invention.

[0067] The present invention provides the following technical solutions, as shown figure 1 As shown, the technology of the present invention provides a video face-changing method, the main contents of which include:

[0068] S100: Preprocessing the input data of the user;

[0069] S200: Adjusting to realize the alignment of the face parts described in the image frame;

[0070] S300: Adjust facial features and skin color after face swapping;

[0071] S400: Realize fusion of facial parts, and output final effect image frames.

[0072] Further, the step S100 includes the following sub-steps:

[0073] Step S...

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 video face changing method and device. The video face changing method comprises the steps of obtaining a to-be-processed image frame, performing key detection on a template image and a to-be-processed user image, adjusting key points to achieve alignment and superposition, migrating fusion of areas such as a face and skin color, restoring other parts, fusing a face contour mask image to a template, and performing replacement to obtain a face-changed image frame. The method can be realized locally, the privacy can be better protected, and the shape problems of light, skin color, five sense organs and the like are solved.

Description

technical field [0001] The present invention relates to the technical field of video processing, in particular to a video face changing method and device. Background technique [0002] With the development of AI technology and deep face-changing technology of artificial intelligence, the core of deep learning AI Deepfakes is to use the noise encoder to identify whether the image has undergone image transformation. In the fake video, it is necessary to perform image transformation processing on the face image of the person. To obtain multiple frames of the person's face image, and then replace the multiple frames of the person's face image with the person's face image in the original video to obtain a forged video, wherein the denoising encoder is based on the first sample person The face image and the second sample face image are obtained by training the self-encoder. [0003] There is another lightweight face-changing algorithm, whose core idea is not to use the method of ...

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): G06K9/00
CPCG06V40/171
Inventor 邓裕强马陈爽区永强周超红刘文卓
Owner GUANGZHOU JIUBANG DIGITAL TECH
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