Unlock instant, AI-driven research and patent intelligence for your innovation.

Abnormal face recognition living body detection method and system based on MCCAE network and Dep SVDD network

A technology of face recognition and liveness detection, which is applied in the field of abnormal face recognition and liveness detection, can solve the problems of waste of manpower and material resources, impossible collection of attack types, 3D mask spoofing attacks, etc., to save manpower and material resources, improve generalization performance, The effect of strong generalization performance

Pending Publication Date: 2021-04-16
声耕智能科技(西安)研究院有限公司
View PDF0 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Because practical face recognition needs to have good resistance to spoofing attacks in various scenarios, but this requires collecting a large number of attack images, which wastes manpower and material resources, and it is impossible to collect attack types in all scenarios
[0004] Printed face photos and face screenshots in video playback are the most common types of spoofing attacks in face recognition, but now more and more 3D mask spoofing attacks appear, making it difficult for us to distinguish them using only RGB image information Real faces and spoofing attacks

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Abnormal face recognition living body detection method and system based on MCCAE network and Dep SVDD network
  • Abnormal face recognition living body detection method and system based on MCCAE network and Dep SVDD network
  • Abnormal face recognition living body detection method and system based on MCCAE network and Dep SVDD network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment approach

[0049] Such as figure 1 As shown, an abnormal face recognition living body detection method based on MCCAE network, including.

[0050] S1. Obtain the same group of multi-channel face data that has undergone image alignment from the data set Unified preprocessing of multi-channel data Among them, the multi-channel data set includes at least the following channels: grayscale image, depth image, near-infrared image, and thermal infrared image.

[0051] S2. Input the processed data into the trained deep self-encoder network MCCAE, use the deep self-encoder network MCCAE to obtain the latent layer features of the real face, and perform image reconstruction for the latent layer features, and the reconstructed The image is output; according to the input image and the output image, the attack score of image reconstruction is calculated;

[0052] S3. Identify whether the input image data is normal face data according to the attack score.

[0053] Specifically, S201, constructing...

specific Embodiment

[0103] This experiment is performed on the WMCA dataset. The dataset contains 1679 real faces and spoofing attack videos of 72 people. There are 347 and 1332 real face data and spoofing attack data respectively. The multi-channel data set contains 4 channels, which are grayscale image, depth image, near-infrared image, and thermal infrared image. Each video sampled 50 frames, and the image resolution was 128x128 pixels. Multi-channel data was registered and image normalization was performed. The invention divides the WMCA data set into a training set (randomly selecting 90% normal faces in the WMCA data set) and a test set (remaining 10% normal face images and spoofing attack images).

[0104] In order to prove the effectiveness and generalization performance of the method, the ROC curve is selected to represent the experimental standard, and by changing the size of the feature dimension L of the latent layer, the optimal result L=256 is finally selected for display.

[010...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention provides an abnormal face recognition living body detection method and system based on an MCCAE network and a Dep SVDD network. The abnormal face recognition living body detection method comprises the following steps: acquiring the same group of multichannel face data subjected to image calibration from a data set; uniformly preprocessing the multi-channel data; inputting the processed data into a trained deep auto-encoder network MCCAE, obtaining the latent features of a real face, carrying out the image reconstruction of the latent features, and carrying out the face recognition; and acquiring network parameters in an MCCAE encoding stage to a Dep SVDD feature extraction network for initialization, and performing further training to map features in a feature domain into a hypersphere for face recognition. And whether the captured face is a real face or a forged face spoofing attack can be judged in a generalized manner, so that the security of the face recognition system can be ensured.

Description

technical field [0001] The invention relates to the technical field of computer vision, in particular to a method and system for abnormal face recognition living body detection based on MCCAE network and Deep SVDD network. Background technique [0002] As a traditional biometric technology, face recognition has been widely used in many fields such as security authentication and e-commerce with the continuous maturity of face recognition technology, such as access control systems in life, smart phone face unlocking and remote transactions etc. However, although the traditional face recognition algorithm can already perform well in recognition accuracy, it cannot resist various spoofing attacks, such as printed face photos, face recognition in video playback, etc. Take screenshots and wear the mask of the target person to forge legal identity information to achieve the purpose of deceiving the face recognition system. [0003] The traditional liveness detection algorithm for...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
IPC IPC(8): G06K9/00G06N3/04G06N3/08
Inventor 张语格陈捷隆弢雷攀李文申
Owner 声耕智能科技(西安)研究院有限公司