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

A face liveness judgment method based on deep learning and video zoom technology

A technology of video amplification and deep learning, applied in neural learning methods, biometric identification models based on physiological signals, instruments, etc., can solve cumbersome problems and achieve high recognition accuracy

Active Publication Date: 2022-05-03
UNIV OF ELECTRONICS SCI & TECH OF CHINA
View PDF8 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

These methods have their own advantages and disadvantages. Cooperative liveness detection is a non-silent detection that requires users to make specified actions, which is relatively cumbersome.

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
  • A face liveness judgment method based on deep learning and video zoom technology
  • A face liveness judgment method based on deep learning and video zoom technology
  • A face liveness judgment method based on deep learning and video zoom technology

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0028] In order to make the purpose, technical solutions and advantages of the present invention clearer, the present invention will be described in further detail below in conjunction with the accompanying drawings and examples. It should be understood that the specific examples described here are only used to explain the present invention, but not to to limit the present invention.

[0029] see Figure 1 to Figure 4 , the present invention is a human face detection system based on deep learning and video amplification technology, including a data acquisition camera, electronic equipment and non-electronic equipment equipped with an attack face, a computer, an Android mobile phone and a set of Android human-computer interaction UI, human-computer The interactive UI is used to process the face image data collected by the mobile phone camera, and judge the authenticity of the currently collected face data by analyzing the image data.

[0030] The data acquisition module includ...

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 discloses a method for judging human face livingness based on deep learning and video amplification technology, and involves image processing, neural network, software development, production and acquisition of data sets. The attack faces used include electronic devices such as tablets, mobile phones, and computers, as well as non-electronic devices such as general photos, posters, and 3D models, including differences in ambient light intensity and distance. The dataset has great generalization. The invention processes the data through the Euler influence amplification algorithm and the convolutional neural network, and writes an interface to achieve real-time identification of the input data, and displays in real time whether the acquired face is a real face or an attack face.

Description

technical field [0001] The invention relates to an intelligent detection technology, covers the field of optical, mechanical, computer and soft computing, and is especially designed for the human face living body detection technology in biometric identification. Background technique [0002] Since Apple demonstrated the FaceID facial unlocking technology for the first time at the press conference at 1:00 am on September 13, 2017, Beijing time, liveness detection technology has entered an era of rapid development. The main function of liveness detection is to distinguish real faces from fake people. Face. Since the face unlocking technology is non-contact, convenient and fast, various fields have launched their own face unlocking technology one after another. In October 2019, the media revealed that there was a major bug in the express cabinet of the domestic Fengchao express company. Fengchao express cabinet A new function of face unlocking express delivery was launched, bu...

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
Patent Type & Authority Patents(China)
IPC IPC(8): G06V40/16G06V40/40G06V10/82G06N3/04G06N3/08
CPCG06N3/08G06V40/166G06V40/45G06V40/15G06N3/045
Inventor 张静郭权浩刘娟秀刘霖杜晓辉倪光明刘永
Owner UNIV OF ELECTRONICS SCI & TECH OF CHINA