Living body detection method and device based on near-infrared camera

Abstract

The invention relates to a living body detection method and device based on a near-infrared camera, and the method comprises the following steps: collecting image data which comprises a color image obtained through a visible light camera and a near-infrared image obtained through the near-infrared camera; positioning a face area on the image data; judging whether the color image is a real face ornot according to the color of the face region in the color image, and traversing pixel points in the face region in the color image according to a screening condition; counting the number of the pixelpoints meeting the screening condition, if the number of the pixel points meeting the condition exceeds a number threshold value, continuing the next step, and otherwise, ending the detection; judging whether the near-infrared image is a real face or not according to the brightness of the face region in the near-infrared image, and traversing pixel points in the face region in the near-infrared image according to a screening condition; counting the number of the pixel points meeting the screening condition, and if the number of the pixel points meeting the condition exceeds a number thresholdvalue, considering that the near-infrared image is a real face; otherwise, ending detection.

Description

technical field [0001] The invention relates to a living body detection method and device based on a near-infrared camera, belonging to the field of face recognition. Background technique [0002] With the vigorous development of face recognition technology, its application scope is becoming wider and wider, and its application in life scenes includes basic necessities of life. However, although the current face recognition technology can identify the identity of the face, it cannot accurately distinguish the authenticity of the input face, and there is a risk of being attacked by a forged face. There are three common ways to forge a face: a picture containing the user's face, a video containing the user's face, a 3D model or a mask headgear made using the user's face. Therefore, it is necessary to perform liveness detection on the recognized face, that is, to judge whether the recognized face is from a real user, or from a picture, video or other fake face containing the u...

AI Technical Summary

Problems solved by technology

Among them, the method based on microtexture is easily affected by light and image resolution, and is easy to be cheated by the video; the method based on motion information requires user interaction, and the user experience is not high; the method based on multispectral uses the spectral reflectance of skin and other materials. Most of them use near-infrared light, which has strong recognition ability and high accuracy rate, but the ability to recognize printed pictures of some special materials is poor

Moreover, most of the current living detection methods based on near-infrared light construct and train deep learning models for living detection. However, this requires a lot of data and time for training, which is costly and complex.

Images