Human face living body detection method

Abstract

The invention discloses a human face living body detection method. The method comprises the steps of obtaining a visible light image and a depth image of a target object; detecting five key points ofthe face area and the face by using a face key point detection algorithm, and cutting out local images of areas corresponding to the visible light image and the depth image according to the coordinates of the key points; respectively inputting the cut local images into local feature network branches, and respectively inputting visible light and depth global images into global feature network branches; after different network branch features are superposed, performing feature fusion, and performing dichotomy by utilizing a classification function to obtain a first processing result and a secondprocessing result; and finally, determining whether the target object is a human face living body or not according to the first processing result and the second processing result.

Description

technical field [0001] The invention relates to the field of image recognition, in particular to a face detection method. Background technique [0002] Biometric systems are widely used in fields such as mobile phone authentication and access control. focus on. Liveness detection refers to feature screening to determine whether the biometric information obtained through the lens is obtained from the corresponding legal live user. The main method of face-based liveness detection is to distinguish the physiological information on living samples. These physiological information are used as important distinguishing conditions to distinguish sample carriers such as paper and silicone plastic, and are also used to distinguish between paper attacks and video attacks. and mask attacks and other attack methods. The main differences between living samples and non-living samples are reflected in color texture, motion deformation, material and image quality. The living body detectio...

AI Technical Summary

Problems solved by technology

[0003] The existing technology basically uses single-mode visible light cameras for liveness detection, but visible light cameras are affected by many factors, such as common light changes, posture changes, etc., and it is difficult to distinguish between 3D face attacks

Second, many liveness detection algorithms use traditional underlying features to classify real and fake faces, but these features are not robust enough and often lead to classification failures

Third, when many methods use depth image information, for convenience, the 16bit depth image is converted to 8bit, which will cause a certain degree of information loss

Images