Method and system for detecting living body human face

Abstract

The invention relates to a method and system for detecting a living body human face. The method comprises the steps of obtaining images from a shot video sequence, detecting a human face in the video images, carrying out location on facial critical areas, randomly selecting one or more kinds of movements in a movement collection through a critical area detection classifier, randomly selecting the completing times of the movements, prompting a user, and determining the user as a living body if the user completes the random selected movements for many times within an appointed time period, otherwise, determining the user as a non-living body. According to the method and system for detecting the living body human face, when living body detection is carried out, the system randomly selects certain movements and randomly appoints the completing times of the movements every time, and therefore the user cannot pass the living body detection by using photos for cheating. In addition, due to the fact that the detected items are selected randomly, the user cannot pass the living body detection through the mode of playing video clips. Therefore, the method and system for detecting the living body human face can better prevent cheating behaviors in the mode such as the photos and the video clips in the living body detection, and the reliability and the safety of the living body detection are made to be higher.

Description

Technical field [0001] The invention belongs to the field of biological feature recognition, and in particular relates to a method and system for detecting a living human face. Background technique [0002] With the rapid development and wide application of biometric identification technology, its security has also been severely challenged, and researchers are paying more and more attention to its security issues. How to ensure that the biological information extracted by the biometric recognition system is obtained from a living user with biological activity and can resist replication or repeated attacks is the focus of many people's attention. Counterfeiters can use plasticine forged fingerprints, face photos, face sketches, face videos, three-dimensional model synthesis and other attack methods to deceive existing biometric systems, thereby deceiving legal identity authentication and engaging in illegal activities. Therefore, if the biometric identification system lacks effec...

AI Technical Summary

Problems solved by technology

[0014] The 3D model has the 3D information of the human face, but this information is rigid and lacks physiological information, and it is very difficult to imitate a 3D model of a living person

This strategy is feasible when the user cheats the liveness detection system by using a blurry or low-resolution picture; however, when the user cheats the liveness detection by using a high-definition picture, this strategy will fail

Because the grayscale, spectrum, texture and other features of the real face and the high-resolution photo face are very close, or even mixed together, it is difficult for the classifier to effectively distinguish the two.

Images