An identification method and device based on hand veins

An identity recognition and vein technology, applied in the field of biometrics, can solve the problems that affect the performance of the recognition algorithm, the accuracy of palm vein or finger vein recognition is not high, and achieve the effect of improving accuracy, quality and robustness.

Active Publication Date: 2021-02-19
TOP GLORY TECH INC CO LTD
View PDF8 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The technical problem to be solved by the present invention is to provide a hand vein-based identity recognition method and device to solve the problem that the recognition accuracy of a single palm vein or finger vein is not high, and the images collected by improper placement can easily affect the performance of the recognition algorithm And other issues

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
  • An identification method and device based on hand veins
  • An identification method and device based on hand veins
  • An identification method and device based on hand veins

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0047] Refer to attached figure 1 As shown, the identification method based on hand veins includes the following steps:

[0048] 1) Use an infrared camera to collect 50 hand vein images of 1,000 hands. The image requires five fingers to be spread open. The collected hand images are single-channel hand vein grayscale images, such as figure 2 shown.

[0049] 2) Convert the single-channel hand vein grayscale image into a three-channel hand vein image, manually mark the hand vein image, and then input it into the full convolutional network FCN to train the model, using the trained full Convolutional Network FCN to segment hand vein images.

[0050] 3) Calculate the curvature of each point on the hand edge contour according to the hand vein image, the specific method is: select the edge contour points ,via calculations with The inner product of two vectors is used to determine the curvature, the smaller the inner product, the greater the curvature of the point, where, wi...

Embodiment 2

[0077] Refer to attached Figure 7 As shown, this embodiment relates to a hand vein-based identification device, which includes:

[0078] A collection module, which uses an infrared camera to collect several hand images with five fingers spread out; the collection module is used to realize the function of step 1) of embodiment 1.

[0079] A segmentation module, which uses a full convolutional network FCN to segment the hand vein image in the hand image; the segmentation module is used to realize the function of step 2) of embodiment 1.

[0080] The fingertip and concave point finding module, which calculates the curvature of each point on the edge contour of the hand according to the hand vein image, and finds the fingertips of five fingers and four concave points between two fingers according to the curvature; fingertips and concave points The point finding module is used to realize the function of step 3) of embodiment 1.

[0081]Correct the cutting module, which utilizes ...

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 present invention relates to an identity recognition method and device based on hand veins. The method includes the following steps: 1) collecting hand images with five fingers spread; 2) segmenting hand vein images; 3) calculating hand edge contours The curvature of each point, find out the fingertips of the five fingers and the concave points between the four fingers; 4) Determine the orientation of the hand and correct it, and crop the hand vein image; 5) Expand and enhance the hand vein image to improve the recognition 6) In the registration stage, input the processed image into the recognition model, extract the image features, and store it in the database; 7) In the recognition stage, input the processed image into the recognition model, extract the image features, and The registered image features are compared to complete the recognition. Compared with palm vein and finger vein recognition, the present invention recognizes the entire hand vein with high accuracy, effectively standardizes images through semantic segmentation and direction correction, and improves the robustness of recognition.

Description

technical field [0001] The invention belongs to the technical field of biological identification in the field of information security, and in particular relates to an identification method and device based on hand veins. Background technique [0002] In recent years, with the development of information technology, vein recognition technology has made great progress. Compared with face recognition technology, vein recognition has the advantages of in vivo characteristics, non-reproducibility, high security level, and large individual differences. At present, vein recognition technology has been used in finance, military industry and other fields, bringing great convenience to people's life. Existing vein recognition algorithms mainly refer to vein recognition and palm vein recognition. [0003] For example, the patent No. CN105975905A discloses a finger vein rapid recognition method, by matching the feature points in one feature point set of finger veins with the feature poi...

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): G06K9/00G06K9/34G06K9/46G06K9/62G06N3/04G06N3/08
CPCG06N3/08G06V40/10G06V40/14G06V10/267G06V10/40G06V10/44G06N3/045G06F18/214
Inventor 赵国栋张烜胡振寰李学双
Owner TOP GLORY TECH INC CO LTD
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