Face generation privacy protection method based on hierarchical k anonymous identity replacement

A face generation and identity replacement technology, which is applied in the field of face image privacy protection, can solve the problem of leaking the target face or target identity, and achieve the effects of privacy protection and aesthetics, effective vision, and high privacy protection

Pending Publication Date: 2022-03-04
HANGZHOU DIANZI UNIV
View PDF0 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0009] (2) The current existing methods mainly use face-changing or use other people's identities to fuse with their own data to achieve anonymity, but after changing faces or identities, the information of the target face or target identity will also be leaked

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 generation privacy protection method based on hierarchical k anonymous identity replacement
  • Face generation privacy protection method based on hierarchical k anonymous identity replacement
  • Face generation privacy protection method based on hierarchical k anonymous identity replacement

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0074] The present invention will be further described below in conjunction with drawings and embodiments.

[0075] Such as figure 1 As shown, the face generation privacy protection method based on hierarchical k anonymous identity replacement, the specific steps are as follows:

[0076] Step 1: Dataset preprocessing:

[0077] 1-1 Use a face detector (dlib or MTCNN) to detect the face area of ​​each image, and crop the face area according to the face coordinates to obtain a cropped image containing only the face to avoid the anonymity effect of background information Impact.

[0078] 1-2 Use the k-means unsupervised clustering method to perform hierarchical clustering on the identity information of the cropped face images to obtain the clustered group id.

[0079] 1-3 Use the existing pre-trained face segmentation network to process the uncropped image, and generate a face segmentation mask for each picture, and stitch the segmented face mask and the uncropped image to obta...

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 generation privacy protection method based on hierarchical k anonymous identity replacement, which comprises the following steps: firstly, preprocessing a face image data set, then constructing a hierarchical k anonymous generative adversarial network structure, and constructing a hierarchical k anonymous objective function; constructing a face replacement generative adversarial network structure, and constructing a target function of face replacement; and finally training and testing by using a public data set to obtain a trained hierarchical k anonymous generative adversarial network and a face replacement generative adversarial network. The replaced target face is also generated through the network, so that privacy of others cannot be invaded, and compared with a conventional mosaic shielding method, the method is more effective and more friendly visually. Experimental results obviously prove the high efficiency and practicability of the method, and the privacy protection of the figure image is more efficient and beautiful.

Description

technical field [0001] The invention relates to the field of face image privacy protection. With the advent of the era of big data and artificial intelligence, the privacy and security of personal images has received more and more attention. Therefore, the present invention proposes a method based on face anonymity, by using the generated proxy data set to replace the face image, so as to achieve the purpose of image anonymity protection. Background technique [0002] In the information age, with the rapid improvement of Internet technology, it is possible to disseminate knowledge and ideas in real time, making the most authentic communication between people a reality. Nowadays, the emergence of high-performance equipment and continuous iteration of technology have made the development of artificial intelligence on the right track. Among them, image processing technology based on deep learning is frequently seen in people's daily life. For example, face recognition, image...

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): G06F21/62G06V40/16G06V10/762G06K9/62G06N3/04G06N3/08
CPCG06F21/6254G06N3/08G06N3/045G06F18/23213
Inventor 匡振中陈超俞俊
Owner HANGZHOU DIANZI UNIV
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