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

Face acquisition system based on edge intelligent perceptron and privacy protection method

A privacy protection and intelligent perception technology, applied in the face acquisition system and privacy protection field based on the edge intelligent sensor, can solve the problems of unfavorable face image application background, unable to reflect face information, etc., to improve security, guarantee Security, the effect of improving the degree of encryption

Pending Publication Date: 2022-04-19
TONGJI UNIV
View PDF0 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

This technology only protects from the perspective of user privacy information, which is not conducive to the application background of face images; if it does not touch the feasibility of face recognition, it is necessary to improve the feature extraction and storage scheme of face images, without affecting At the same time as the feature extraction effect of the network, noise processing and feature fusion are performed on the feature map, so that the feature cannot reflect the real face information, forming the protection of face features. On the other hand, for the situation of large-screen display, the large-screen Users should only be able to see their own face area, blur other faces captured by the camera, and then display them on the screen

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 acquisition system based on edge intelligent perceptron and privacy protection method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0035] like figure 1 As shown in Fig. 1, a face acquisition system based on edge perceptron, the system includes edge perceptron, semantic transmission network, face feature cloud database and visual terminal.

[0036] A privacy protection method using a face collection system based on an edge intelligent sensor, including face encryption and face decryption, wherein the process of face information encryption includes:

[0037]The edge sensor obtains the face image, uses the face recognition network to detect and recognize the face image, and obtains multiple face regions in the face image; the face semantic features hidden in the face image are obtained during the reasoning process of the face recognition network ; Use the feature extraction result of the face reference image in the face data set to perform noise processing, and superimpose it with the face reference image to protect the currently detected face semantic features; store the face area after blurring , to prote...

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 relates to a face acquisition system and privacy protection method based on an edge intelligent perception body, and the method comprises a face encryption process and a face decryption process, and the face information encryption process comprises the steps: obtaining a face image through the edge perception body, and obtaining a plurality of face regions in the face image; performing noise processing by using the feature extraction result of the face reference image, and performing superposition to protect the semantic features of the face; carrying out fuzzy processing on the face region and then storing the face region; in the face information decryption process, the visual terminal recognizes the face semantic features of a terminal user to form a decryption key, the face feature cloud database is traversed through a spatial-temporal index to carry out key matching, face feature self-decryption face pairing is achieved, then the encrypted video is presented through the generative adversarial network associated with the semantic features, and the face information is decrypted through the generated adversarial network associated with the semantic features. And multi-face targeted decryption in the image is realized. Compared with the prior art, the method has the advantages of image localization distributed storage, face feature cloud edge collaborative encryption, low-delay semantic transmission and the like.

Description

technical field [0001] The present invention relates to the technical field of image processing and face recognition, in particular to a face collection system and privacy protection method based on edge intelligent sensors. Background technique [0002] With the rapid development of artificial intelligence and computer vision, vision-based intelligent applications gradually occupy the market, and related application directions based on image classification, object detection and other sub-fields emerge in an endless stream, and computer vision technology has gradually integrated into our lives. [0003] With the continuous progress and development of big data application technology in modern society, the application of face recognition technology in the public domain has become an inevitable trend. While bringing convenient applications, it will also cause the loss of private information of face images. The combination of the information sharing and interactivity of the Inte...

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): G06V40/16G06N3/04G06K9/62G06V10/30G06V10/774G06F21/60
CPCG06F21/602G06N3/045G06F18/214
Inventor 何斌丁跃尘朱忠攀陆萍
Owner TONGJI 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