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

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...

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

Images