Human face living body detection method and device and computer readable storage medium

Abstract

The invention discloses a human face living body detection method and device and a computer readable storage medium. The method comprises the following steps of S1, processing a to-be-detected pictureto serve as input of a convolutional neural network model; and S2, convoluting on the to-be-detected picture to obtain convolution output; S3, inputting the convolution output into the classificationmodel for analysis to obtain a feature vector of the to-be-detected picture; S4, determining a picture sample matched with the to-be-detected picture from each pre-acquired picture sample; S5, takingthe label of the picture sample matched with the to-be-detected picture determined in the step S4 as the label of the to-be-detected picture to obtain a detection result of the to-be-detected picture. The single-frame picture is used as living body detection input, so that the method is simple and easy to use, and industrial application and upgrading and reconstruction of old projects are facilitated; and the feature component extraction and deep learning technology is utilized to improve the accuracy and speed of living body detection.

Description

technical field [0001] The present invention relates to the technical field of biometric identification, in particular to a human face living body detection method, device and computer-readable storage medium. Background technique [0002] Face recognition is a popular research field of biometric technology. Compared with other biometric technologies, face recognition technology has the advantages of non-contact and friendliness. Face recognition systems have been used in more and more occasions, such as mobile terminal unlocking systems, computer boot login systems, and access control systems. In addition, face recognition is also used in criminal investigation, surveillance systems and other fields. However, behind the rapid development of face recognition technology, there are huge security risks. The face recognition system can determine the true identity of the face, but it cannot determine whether the face image in front of the camera is from a legitimate user or an ...

AI Technical Summary

Problems solved by technology

[0003] There are many existing face detection methods, for example: based on structured light and binocular detection methods, although this method has high accuracy, it requires high hardware costs and technical requirements, which is not conducive to industrial applications and old projects upgrade of

Machine learning method: Some traditional machine learning methods use HSV or YCRCB color space input, and after LBP (local binary pattern), SVM (Support Vector Machine) classification is used to judge whether it is a living body. Although the hardware cost and technical requirements of this method Low, but the learned features are insufficient, resulting in low accuracy

In addition, some machine learning methods use RGB color space input, and after convolutional neural network processing, the classification probability of real people and dummy people can be obtained to judge whether they are living or not. However, the disadvantage of this method is the difference between living and non-living in RGB color space. It is not obvious, which is not conducive to the training and analysis of the deep learning network, and the accuracy of the traditional binary classification method for the detection of living and non-living is low

Images