Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Biometric feature living body recognition detection method and device based on depth image

A deep image and biometric technology, applied in character and pattern recognition, instruments, computing models, etc., can solve problems such as poor robustness, high hardware computing performance requirements, and large amount of computing, and achieve both robustness and efficiency Effect

Pending Publication Date: 2021-04-16
HANGZHOU HIKVISION DIGITAL TECH
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0008] The existing depth image-based biometric living body recognition detection method uses a convolutional neural network to extract depth image features, which requires a large amount of calculation, requires high hardware computing performance, and has a long response time; while using the original pixel value of the depth image to reduce the dimensionality as Image features, image features are relatively simple, poor robustness

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
  • Biometric feature living body recognition detection method and device based on depth image
  • Biometric feature living body recognition detection method and device based on depth image
  • Biometric feature living body recognition detection method and device based on depth image

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0110] see figure 1 as shown, figure 1 It is a schematic flow chart of the applicant's face recognition detection method.

[0111] Step 101, acquiring a depth image sample containing a detected target;

[0112] The detected target image is collected through the depth camera, for example, the face depth image is collected through the depth camera, and the face area in the image is detected. If multiple faces are detected, the face with the largest area is selected.

[0113] Based on the selected face, the depth image of the face area is cut out. For the position point where the depth value fails to be obtained, the depth value of the pixel points in the neighborhood around the position point is used to repair according to interpolation; if the pixel values ​​​​of an area are obtained If it fails, the depth value of the edge of the area will be repaired first, and then gradually repaired to the center of the area, that is, for any pixel point on the edge of the area, the depth...

Embodiment 2

[0148] see Figure 6 as shown, Figure 6 It is a schematic flow chart of the applicant's face recognition detection method.

[0149] Step 601, acquiring a depth image sample containing a detected target; this step is the same as step 101;

[0150] Step 602, in order to reduce the influence of the background in the face picture, based on the depth image, locate l key points in the face according to the depth value: (x 1 ,y 1 ), (x 2 ,y 2 ), ... (x l ,y l ),

[0151] In this step, since there are obvious differences in the depth values ​​of parts with three-dimensional effects such as facial features, including but not limited to, nose, eyes, mouth, lips, etc., and the combination of these parts, based on this , the feature points of the parts with strong three-dimensional effect can be located as key points.

[0152] Step 603, intercept the size of W around each key point l ×H l At least one sub-region of is used as a key point neighborhood; for each pixel in each ne...

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 biometric feature living body recognition and detection method based on a depth image, and the method comprises the steps: obtaining the depth image of a detected target which currently comprises biometric features, and carrying out living body recognition of the current depth image based on a trained machine learning model, calculating the gradient of pixel points in the depth image based on the depth image sample, and obtaining image gradient features representing the change degree of the image depth value; obtaining a sub-region gradient direction histogram of the gradient amplitude of at least one sub-region image distributed in the gradient direction according to the image gradient characteristics; connecting all the sub-region gradient direction histograms in series to obtain extracted image features; and taking the image features as a sample of the machine learning model, and training the machine learning model. The invention is simple in algorithm and short in response time, realizes presentation attack detection, and improves the security of identification equipment.

Description

technical field [0001] The present invention relates to the field of image recognition and detection, in particular, to a biometric living body recognition and detection method based on a depth image. Background technique [0002] Living body recognition detection is mainly carried out by identifying the biometric information on the living body. It uses the biometric information as a vital feature to distinguish biometrics forged with non-living substances such as photos, silica gel, and plastics. In layman's terms, in the process of recognition and detection, it is determined that the detected target is indeed a "living body", not a photo, video or anything else. [0003] Take the recognition and detection of human face as an example. A single face recognition based on visible light is easily compromised by faces in photos and videos, does not have anti-counterfeiting functions, and has low security. At present, face detection technologies mainly include interactive actio...

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): G06K9/00G06K9/46G06N20/00
Inventor 邹保珠王升国赵先林
Owner HANGZHOU HIKVISION DIGITAL TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com