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

A Video Privacy Protection Method Based on Expression Fusion

A privacy protection and facial expression technology, which is applied in the direction of TV, color TV, color TV parts, etc., can solve the problems of face image expression changes, etc., to achieve the effect of protecting private information and protecting expressions

Inactive Publication Date: 2019-03-15
XIDIAN UNIV
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] The purpose of the present invention is to provide a video privacy protection method based on facial expression fusion, aiming to solve the problem that the traditional method of directly merging human faces can ensure that important information is not leaked, but in the process of fusion, the original face image The problem that the expression will change

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
  • A Video Privacy Protection Method Based on Expression Fusion
  • A Video Privacy Protection Method Based on Expression Fusion
  • A Video Privacy Protection Method Based on Expression Fusion

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0052] Refer to attached figure 2 , the concrete steps of the embodiment of the present invention are as follows:

[0053] 1. Facial expression recognition process

[0054] Step 1, the establishment of expression library:

[0055] The JAFFE Japanese adult female facial expression database containing 213 images of 7 different expressions of 10 women was used for expression recognition. There are 2 to 4 images for each expression, all of which are 256×256 8-bit grayscale images.

[0056] Step 2, image acquisition:

[0057] Obtain a continuous sequence of still images from a camera or other device during live video.

[0058] Step 3, image preprocessing:

[0059] Subsampling and grayscale equalization are performed on face images. Through sub-sampling, irrelevant areas in the image are removed, and only facial areas that can reflect expression changes such as eyes, mouth corners, and eyebrows are retained. Then, the histogram equalization process is performed on the image. Af...

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 video privacy protection method based on facial expression fusion. The video privacy protection method based on facial expression fusion detects human faces in real time and recognizes human facial expressions in live video broadcasting. The face image is fused to protect the privacy of the face while ensuring that the facial expression does not change. The present invention not only protects the privacy information of the face, but also retains the original expression of the face by merging with the face images with the same expression in the expression database under the condition that the expression remains unchanged. Under the premise, the integrity of the original face information is improved. Different from the previous method of directly merging the whole face, the expression in the face is fused through the expression library, which realizes the protection of information under the condition that the facial expression remains unchanged.

Description

technical field [0001] The invention belongs to the technical field of video privacy protection, and in particular relates to a video privacy protection method based on expression fusion. Background technique [0002] In recent years, with the rapid development of the Internet and the increasing popularity of various video applications, video personal privacy protection has received widespread attention. Not disclosing private information while ensuring video applications is a hot topic in current research. Due to its high academic value and huge application potential, video privacy protection technology has attracted the attention of scholars. The traditional method of directly merging the entire face uses the image fusion method on the face image to combine the face image with Another face image that does not contain important information is fused, so that the face image that needs to be protected is gradually converted into another image, thereby protecting the important...

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 Patents(China)
IPC IPC(8): H04N5/232G06K9/00G06F16/50
CPCG06F16/583G06V40/174G06V20/46H04N23/611H04N23/6845
Inventor 王祥熊琛裴庆祺
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