Face living body detection network training method and device

Abstract

The invention provides a face living body detection network training method and device, and the method comprises the steps: obtaining face images of a plurality of domains, each domain comprises a plurality of face images, and the plurality of face images in each domain are collected in a same environment scene and / or employing a same data collection device; selecting at least one domain from the plurality of domains as a source domain; inputting the face image in the source domain into an adversarial sample generation network to generate an adversarial sample image; and taking the face image in the source domain as training data, taking the adversarial sample image as test data, and training a to-be-trained face in-vivo detection network to obtain a trained face in-vivo detection network. According to the method and the device, a large number of adversarial samples can be obtained through the face images collected by various environment scenes and / or various types of data collection equipment, the adversarial samples are used for training the face in-vivo detection network, and the robustness of the trained face in-vivo detection network model is improved.

Description

technical field [0001] Embodiments of the present invention relate to the technical field of artificial intelligence, and in particular, to a method and device for training a face liveness detection network. Background technique [0002] In recent years, people have paid more and more attention to face liveness detection technology, because with the application and promotion of face recognition technology in life, the accompanying security issues cannot be ignored. With the advancement of computer technology and the development of artificial intelligence, face detection technology is also constantly improving and improving. At present, face detection technology relying on deep learning and big data technology has become the mainstream method. [0003] In order to improve the stability of face live detection technology and the ability to deal with new attacks, the training method of the existing face live detection network model mentioned that by collecting real face data an...

AI Technical Summary

Problems solved by technology

[0005] Embodiments of the present invention provide a training method and device for a live face detection network, which is used to solve the difficulty in obtaining data for training the live face detection network model in the prior art, resulting in poor robustness of the trained face live detection network model The problem

Images