Face liveness detection method, device, electronic equipment and storage medium

Abstract

This application is applicable to the field of artificial intelligence, and provides a human face living body detection method, device, electronic equipment and storage medium. The face detection method includes: obtaining a face detection image, the face detection image includes an infrared image and a depth image of a human face; performing feature extraction on the infrared image to obtain a global infrared classification feature and a local infrared classification feature; performing feature extraction on the depth image Extraction to obtain global depth classification features and local depth classification features; feature splicing of global infrared classification features and global depth classification features to obtain global multimodal features, and feature splicing of local infrared classification features and local depth classification features to obtain local Multi-modal features; each classification feature is input into a corresponding classifier to obtain a corresponding classification result; if the classification result satisfies a preset condition, it is determined that the face in the face detection image is a live face. Through feature complementarity in multiple dimensions, the accuracy of face liveness detection is improved.

Description

technical field [0001] The present application belongs to the field of artificial intelligence, and in particular relates to a face detection method, device, electronic equipment and storage medium. Background technique [0002] With the continuous development of artificial intelligence technology, the use of human biological characteristics for identification has been widely used. Because of the advantages of initiative and non-invasiveness, face recognition plays an important role in biometric identification. For example, facial recognition payment, facial recognition mobile phone unlocking, high-speed rail facial recognition entry and 3D facial recognition door locks, etc. However, it is becoming more and more common to use counterfeit faces (such as face photos, videos, face masks, and face models) to attack face recognition systems, which brings more and more challenges to face recognition technology. . Therefore, identifying whether a face image is a live face is a n...

AI Technical Summary

Problems solved by technology

Existing live face detection methods cannot adapt to live face detection in different environments, so the accuracy of face recognition is not high

Images