Human face recognition living body detection method for calculating sight line direction based on three-dimensional eyeball model

Abstract

The invention discloses a human face recognition living body detection method for calculating a sight line direction based on a three-dimensional eyeball model. The method comprises the steps of obtaining a human face image forming an expected sight line direction; detecting a human face in the image, obtaining human face feature points, and extracting an eye region of the human face; detecting the center and radius of the eyeball, establishing a three-dimensional eyeball model, extracting the iris edge for circle fitting, and determining the final iris center; obtaining an iris center and an eyeball center, and calculating to obtain a sight line direction; comparing the calculated line-of-sight direction with an expected line-of-sight direction, and if the calculated line-of-sight direction is inconsistent with the expected line-of-sight direction, determining that the target face is a non-living body; and if so, determining that the target face is a living body. The calculation method is simple, the requirement for images is low, and the accuracy and efficiency of living body detection are greatly improved.

Description

technical field [0001] The invention belongs to the technical field of face recognition, and in particular relates to a face recognition living body detection method and system based on a three-dimensional eyeball model to calculate a line of sight direction. Background technique [0002] With the development of science and technology, the Internet of things in living and housing, the modernization of high-rise office buildings, the increasingly developed and diversified means of transportation, etc., these undoubtedly affect all aspects of people at all times, so that people's attention to social security and family residences Safety is more worrying; government departments and public places such as airports, high-speed rail stations, subway stations, and customs have increasing demands for crowd control, public security management, and potential crime analysis; large public places such as stadiums, football fields, or financial centers such as CBD The monitoring of people ...

AI Technical Summary

Problems solved by technology

[0004] (1) The motion-based method mainly analyzes the motion trend of the image frame sequence to determine the background of the image or the unconscious action of the user, but the calculation process is complicated

[0005] (2) Texture-based methods, mainly by finding out the salient distinguishing features of single-frame real faces and spoofed faces for liveness judgment, because spoofed faces will cause quality degradation, blurring, etc. in the process of secondary acquisition Variations in microtexture, but it can only handle low-resolution print photo attacks, not high-resolution photos

This method is divided into a feature layer fusion method and a score layer fusion method. The feature layer fusion method is to fuse multiple features in series and is in the research stage, while the score layer fusion method is to obtain the scores of multiple features and then weight them. The final score is obtained, but for features of different dimensions and different meanings, it cannot be accurately fused, which affects the efficiency and accuracy of living body recognition

[0007] Therefore, the current liveness detection method has shortcomings such as complex calculation methods and strict requirements on images, which seriously affect the accuracy or efficiency of liveness detection.

Images