Anti-deception three-dimensional face recognition method based on information fusion

Abstract

The invention discloses an anti-deception three-dimensional face recognition method based on information fusion. The anti-deception three-dimensional face recognition method comprises: 1, collecting and processing color images and depth images of a plurality of real faces; 2, establishing Gaussian distribution models of a plurality of real faces according to the depth information of the key pointsin each depth map, and determining a threshold range of Gaussian distribution parameters of the real faces; 3, establishing a Gaussian distribution model of the to-be-recognized face, comparing and judging the Gaussian distribution model parameters of the to-be-recognized face with the threshold range of the Gaussian distribution parameters of the real faces, if the to-be-recognized face is judged to be the real face, executing the step 4, and otherwise, not performing face recognition; 4, constructing a deep convolutional neural network and training the deep convolutional neural network; and5, inputting the to-be-recognized face image into the trained deep convolutional neural network for recognition, and outputting a recognition result. By analyzing and modeling the face depth information and fusing the face depth information at the data end, a lightweight network is constructed, and the performance of the whole face recognition system is improved.

Description

technical field [0001] The invention belongs to the technical field of face recognition, and relates to an anti-spoofing three-dimensional face recognition method based on information fusion. Background technique [0002] At present, face recognition systems have been widely used in access control, identity deduplication, video surveillance and other fields. However, most face recognition methods are based on two-dimensional images for identity discrimination. Two-dimensional face recognition still faces huge challenges in an unconstrained environment, such as posture changes, illumination changes, expression changes, camouflage changes, plastic surgery changes, etc., and it is more important for departments such as control areas , face anti-counterfeiting technology is particularly important. Compared with two-dimensional face recognition, three-dimensional face recognition can use three-dimensional depth information to have stronger robustness to the above changes and fac...

AI Technical Summary

Problems solved by technology

[0003] For face anti-counterfeiting, the current main methods are: 1) detection based on motion information, such as activity detection through eye blinking and mouth movement; 2) texture-based analysis, such as Fourier spectrum analysis and Gaussian filtering, etc., this method It is easily affected by illumination and image resolution, and has poor effect on video attacks; 3) Detection is based on multi-spectral reflection, which has strict requirements on acquisition conditions, and the cost of multi-spectral images is higher than that of visible light systems; 4) Based on feature fusion The detection, such as combining motion analysis and face texture to judge, this method has a higher detection rate but a longer average processing time, and has higher hardware requirements

[0004] The above methods have high requirements on equipment and cannot efficiently distinguish whether the collected photos are from real faces in front of the camera, printed photos, or pre-recorded videos, etc.

At present, better 3D face recognition is realized based on the feature fusion method of deep learning, but this will cause the original image information to be seriously lost during the propagation of the deep neural network, resulting in a decline in the overall recognition rate

Images