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

Method for realizing generative false face image identification based on deep convolutional neural network

A face image and neural network technology, applied in the field of generative false face image identification based on deep convolutional neural network, can solve the problem that it is difficult to find false images, achieve broad application prospects, simple network structure, and identification speed fast effect

Active Publication Date: 2020-08-28
THE THIRD RES INST OF MIN OF PUBLIC SECURITY
View PDF3 Cites 7 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The traditional method of identifying fake face images directly learns binary bit classifiers, but for the face images generated by various neural network-based generative models, it is difficult to find common discriminative features for judging fake images from different generative models , so traditional false face image identification methods cannot be well applied to various face images generated by current emerging technologies

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 for realizing generative false face image identification based on deep convolutional neural network
  • Method for realizing generative false face image identification based on deep convolutional neural network
  • Method for realizing generative false face image identification based on deep convolutional neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0030] In order to describe the technical content of the present invention more clearly, further description will be given below in conjunction with specific embodiments.

[0031] The method for realizing generative false face image identification based on deep convolutional neural network of the present invention comprises the following steps:

[0032] (1) Use the mainstream face generation model to generate fake faces;

[0033] (2) Perform pairwise preprocessing on the real face for training and the generated face picture data set, and formulate labels;

[0034] (3) Building a common feature extraction network and a classification network based on a deep convolutional neural network;

[0035] (4) Utilize contrastive loss, to common feature extraction network input training, train with paired face image;

[0036] (5) The common feature extraction network after training is cascaded with the classification network, and the input generated or real single face image is trained;...

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 method for realizing generative false face image identification based on a deep convolutional neural network. The method comprises the following steps: generating a false face by utilizing a mainstream face generation model; performing paired preprocessing on the real face for training and the generated face picture data set, and making a label; constructing a common feature extraction network and a classification network on the basis of the deep convolutional neural network; inputting paired face images for training into the common feature extraction network for training by using the comparison loss; cascading the trained common feature extraction network with a classification network, and inputting a generated or real single face image for training; and carrying out generative false face image identification according to the cascade network model obtained after training. By adopting the method for realizing generative false face image identification based on the deep convolutional neural network, the established network is simple in structure and high in identification speed, and has a wide application prospect in the fields of false biological characteristic image identification and face image security.

Description

technical field [0001] The invention relates to the field of computer vision, in particular to the field of image forgery identification, and specifically refers to a method for realizing generative false face image identification based on a deep convolutional neural network. Background technique [0002] With the development of artificial intelligence technology, video / image tampering technology has brought convenience to human life, but it has also caused great concern in social public safety. In the field of computer vision, all kinds of images generated by various excellent generative models can be used to generate tampered videos or fake pictures for specific people and inappropriate events, especially fake face images, which will produce harmful effects. Very harmful effects on individuals, which may even affect the safety of individuals. The traditional method of identifying fake face images directly learns binary bit classifiers, but for the face images generated by...

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
IPC IPC(8): G06K9/00G06N3/04G06N3/08
CPCG06N3/08G06V40/168G06V40/172G06N3/045Y02T10/40
Inventor 王立刘辛宇姚斌洪丽娟成云飞冯宗伟李明华寅
Owner THE THIRD RES INST OF MIN OF PUBLIC SECURITY
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