Human face living body detection method and device, equipment and medium

Abstract

The invention discloses a human face living body detection method and device, equipment and a medium. The human face detection method comprises the steps of obtaining a training set; inputting the training data into a teacher network for first training to obtain a trained teacher network model; inputting the training data into a student network for second training to obtain a trained face living body detection model; and inputting the to-be-detected face image into the face living body detection model to obtain a detection result whether the object in the face image is a living body or not. According to the invention, the knowledge distillation learning device is used to guide the student network to carry out training, the student network model with fewer model parameters is obtained as the trained face living body detection model, and the calculation speed of the model and the speed of face living body detection are improved; the training process of the human face living body detection model is assisted by updating and optimizing the model parameters through the meta-learning device, and the universality is better. The method and device can be widely applied to the field of artificial intelligence.

Description

technical field [0001] The present invention relates to the field of artificial intelligence, in particular to a face detection method, device, equipment and medium. Background technique [0002] Liveness detection refers to the computer to determine whether the detected face is a real face or a fake face attack, such as various print photo attacks (including color print photos, black and white print photos, infrared print photos, etc.), screen playback attacks ( Mobile phone screens, tablet screens, computer screens, etc.) and high-definition 3D attacks (masks of various materials, head models, headgear masks, etc.), etc. In this regard, various computer vision-based liveness detection methods have emerged. [0003] With the development of deep learning, deep learning methods in artificial intelligence have been applied to the field of live detection due to their powerful and flexible feature extraction capabilities and have gradually become the mainstream method of live d...

AI Technical Summary

Problems solved by technology

At present, the liveness detection method based on deep learning needs to train multiple liveness detection models for different scenarios, that is, it needs to be customized for specific scenarios, and the versatility is not high; more model parameters are required, which leads to slower calculation speed of the model , it is difficult to run in real time on terminal platforms with low computing power (such as embedded devices, etc.)

Images