Living body detecting method and system applied to human face recognition

Abstract

The invention relates to photo cheat-preventing living body detecting method and system which can be used for identity authentication application based on human face recognition. The system comprises an intermediate-frequency filter, a frequency-domain converter and a classifier, wherein the intermediate-frequency filter can adopt a DoG (Difference of Gaussian) filter and is used for carrying out filtering pretreatment on an image to obtain intermediate frequency band information; the frequency-domain converter can adopt a Fourier converter and is used for extracting Fourier transform characteristics from the pretreated two-dimensional image; and the classifier can adopt a logistic regression classifier and is used for judging whether the image acquired from the identity authentication is a real human face or a photo human face. Proved by test results, the method and the system can favorably solve the problem of photo cheat in the identity authentication based on human face recognition under the conditions of no addition of additional auxiliary equipment, no need of active matching of a user, simple realization, less calculated amount and independent function.

Description

technical field [0001] The present invention relates to the sub-field of face recognition in the field of biological pattern recognition, and in particular, to a method and technology of how to distinguish a real face from a photo in a face recognition system; the present invention also relates to the field of machine learning in specific embodiments. and image processing. Background technique [0002] The security of the use of biometric identification systems is a common concern, and people's confidence and acceptance of biometric identification systems largely depends on the system's robustness, low error rate, and anti-spoofing ability. In biometric systems, the most common form of deception occurs at the user interface. An impostor uses some fake signature with the same manifestation to break into a system. [0003] Among various biometric-based applications, face recognition is widely welcomed because it conforms to the way humans distinguish different people and is ...

AI Technical Summary

Problems solved by technology

[0006] 1. Analyze the difference in image information between a real face and a photo face, such as judging whether it is a real person based on the three-dimensional depth information of the head. This method has the disadvantages of not being easy to capture the features required for liveness detection, and the cost of computing time is high;

[0007] 2. Analyze the non-rigid motion changes of the real face, such as using the linear optical flow method to capture the subtle motion information of the three-dimensional face, the movement analysis of the lips when vocalizing, the changes in the eye area, the head motion changes, etc. These methods require The user's active cooperation may require a large calculation time and space overhead;

[0009] In addition, in the above method, there is still the problem that it cannot be used as an independent module, and other modules need to be changed to join the existing face recognition system.

Images