Method and device for identifying forged face picture, computer equipment and storage medium

A technology of image recognition and human face, applied in the computer field, can solve the problem of single type of forged human face

Pending Publication Date: 2021-12-07
EVERSEC BEIJING TECH
View PDF0 Cites 7 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] Embodiments of the present invention provide a method, device, computer equipment, and storage medium for identifying fake face pictures, which solves the problems of single types of fake faces in public data sets and the possibility of network overfitting, and realizes data enhancement and Meet the needs of deep forgery detection and identification

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
  • Method and device for identifying forged face picture, computer equipment and storage medium
  • Method and device for identifying forged face picture, computer equipment and storage medium
  • Method and device for identifying forged face picture, computer equipment and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0030] Figure 1a It is a flow chart of a method for identifying a fake face picture provided by Embodiment 1 of the present invention. This embodiment is applicable to the problem of synthesizing a variety of fake faces by using the data enhancement method of genuine and fake face synthesis to train a fake face picture recognition model with better recognition effect. The method of this embodiment can be executed by a device for identifying fake face pictures, which can be implemented in the form of software and / or hardware, and can generally be integrated into a terminal or server with data processing functions.

[0031] Correspondingly, the method specifically includes the following steps:

[0032] S110. Obtain a deepfake data set. The deepfake data set includes a plurality of video pairs, and each video pair includes a real video and a fake video obtained by replacing a real face in the real video with a face.

[0033] Among them, the deep fake data set is a data set made...

Embodiment 2

[0098] figure 2 It is a structural diagram of an identification device for a fake face picture provided in Embodiment 2 of the present invention. The identification device for a fake face picture provided in this embodiment can be realized by software and / or hardware, and can be configured in a terminal Or implement a method for identifying fake human face pictures in the embodiment of the present invention in the server. Such as figure 2 As shown, the device may specifically include: a deep fake data set acquisition module 210 , an image enhancement processing module 220 , a fake face picture recognition model formation module 230 and a result recognition module 240 .

[0099]Among them, the deep fake data set acquisition module 210 is used to obtain the deep fake data set, the deep fake data set includes a plurality of video pairs, each video pair includes a real video, and replaces the real face in the real video with a face The fake video obtained after;

[0100] The ...

Embodiment 3

[0131] image 3 It is a structural diagram of a computer device provided in Embodiment 3 of the present invention. Such as image 3 As shown, the device includes a processor 310, a memory 320, an input device 330, and an output device 340; the number of processors 310 in the device may be one or more, image 3 Take one processor 310 as an example; the processor 310, memory 320, input device 330 and output device 340 in the device can be connected by bus or other methods, image 3 Take connection via bus as an example.

[0132] The memory 320, as a computer-readable storage medium, can be used to store software programs, computer-executable programs and modules, such as program instructions / modules corresponding to the method for identifying fake face pictures in the embodiment of the present invention (for example, deep fake data Set acquisition module 210, image enhancement processing module 220, fake face picture recognition model formation module 230 and result recogniti...

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 embodiment of the invention discloses a method and a device for identifying a forged face picture, computer equipment and a storage medium. The method comprises the steps: acquiring a deep counterfeit data set, wherein the deep counterfeit data set comprises a plurality of video pairs, and each video pair comprises a real video and a counterfeit video obtained by performing face replacement on a real face in the real video; forming a plurality of negative sample images according to the real face and the replacement face, and forming a plurality of positive sample images according to the real video; constructing a training sample set according to each negative sample image and each positive sample image, and training a machine learning model to form a fake face image recognition model; inputting a to-be-recognized target face picture into the recognition model, and obtaining a recognition result about whether the target face picture is a forged face picture or not. According to the embodiment of the invention, the problems that the type of a public data set counterfeit face is single and the network over-fitting possibility exists are solved, data enhancement is realized, and the requirements of deep counterfeit detection and recognition are met.

Description

technical field [0001] Embodiments of the present invention relate to the field of computer technology, specifically to the fields of deep learning, computer vision, deep forgery generation and deep forgery detection, and in particular to a method, device, computer equipment and storage medium for identifying fake human face pictures. Background technique [0002] The field of deepfake detection aims at counter-reconnaissance of deepfake generation techniques. According to the object type, the current main methods can be divided into two categories: picture level and video level. [0003] Most of the models of image-level detection and recognition methods rely on the same data distribution, and are weak in the face of unknown tampering types. The video-level detection and recognition method works well and can detect a small amount of tampering in the video, but it is very sensitive to video preprocessing, such as video compression, light changes, etc., and such methods cann...

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): G06K9/00G06K9/62G06N20/00
CPCG06N20/00G06F18/214
Inventor 王佳琪李玉惠傅强蔡琳阿曼太梁彧马寒军田野王杰杨满智金红陈晓光
Owner EVERSEC BEIJING TECH
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