Non-interactive monocular living body detection method

A liveness detection, non-interactive technology, applied in spoofing detection, character and pattern recognition, instruments, etc., to achieve the effect of good compatibility and economy, good applicability, use cost and effectiveness balance

Inactive Publication Date: 2020-10-13
贵阳像树岭科技有限公司
View PDF13 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0007] The purpose of the present invention is to provide a non-interactive monocular living body detection method to solve the strong demand for live body detection in identity verification of a hardware device face recognition system with only a monocular RGB camera, such as human-machine verification, mobile applications, web applications and numerous mobile smart terminals, home personal computers and access control systems, etc.

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
  • Non-interactive monocular living body detection method
  • Non-interactive monocular living body detection method
  • Non-interactive monocular living body detection method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0048] Such as Figure 1-4 , a non-interactive monocular liveness detection method, comprising the following steps:

[0049] (1) Gather continuous frame images of people's faces to obtain RGB image sequences, and collect continuous frame images containing people's faces for 5s;

[0050] (2) By using the face detection algorithm, find the face contained in the image, and at the same time use the feature point alignment project to align the target objects in each frame to obtain the image face_image of the face area of ​​the same size M×N And the background image nonface_image of the non-face M×N ;

[0051] (3) The image sequence of each face area and the background image sequence of non-face are subjected to mean value filter processing:

[0052]

[0053] Among them, raw_image(m, n) represents the original image, denoise_image(x, y) represents the image after denoising, and the coordinates of the pixel points are represented in brackets, P xy Represents a filter window w...

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 non-interactive monocular living body detection method, and belongs to the field of security and protection recognition, being applied to living body detection of RGB face images and IR face images, for solving the strong requirements of hardware equipment only provided with a monocular RGB camera for living body detection in face recognition and identity verification, such as the fields of man-machine verification, mobile applications, web applications, numerous mobile intelligent terminals and the like. The non-interactive monocular living body detection method mainly comprises the steps of collecting continuous images, performing face detection to obtain a Face set and a Background set, carrying out equalization filtering denoising, using a Butterworth filter to filter out signals in a non-heart-rate frequency band, obtaining a two-dimensional power signal-to-noise spectrum image through a face PPG-Map scheme, finally establishing a classifier for data of living body and prosthesis faces in a deep learning model, and completing the living body detection target in the real scene. The non-interactive monocular living body detection method achieves good balance in use cost and effectiveness, and can effectively prevent forged face identity attacks of portrait photos, portrait videos, masks and the like.

Description

technical field [0001] The invention provides a non-interactive monocular living body detection method, which belongs to the field of security recognition and is applied to living body detection of RGB human face images and IR human face images. Background technique [0002] In recent years, the commercial application of face recognition technology has become more and more widespread. However, it is very easy to use photos, videos, three-dimensional masks, etc. to fake faces. Therefore, face liveness detection is an important issue in the security of face recognition and authentication systems. From the perspective of the types of image acquisition equipment for live detection, the current common live detection is mainly two types of visible light image acquisition and multi-spectral image acquisition, among which multi-spectral image acquisition includes near-infrared, far-infrared, thermal infrared and other imaging equipment; from In terms of the implementation methods of...

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 Applications(China)
IPC IPC(8): G06K9/00G06K9/40
CPCG06V40/161G06V40/168G06V40/172G06V40/45G06V10/30
Inventor 李丹疆刘萍黎平
Owner 贵阳像树岭科技有限公司
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap