Finger vein recognition method and device and storage medium

A finger vein and identification method technology, applied in the field of biometric identification, can solve the problems of low finger vein identification accuracy, large differences in the structure of finger vein maps, affecting the finger vein identification accuracy, etc. Effect

Pending Publication Date: 2020-11-17
SHENZHEN POLYTECHNIC
View PDF0 Cites 10 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

But in fact, the detail points of finger veins are not stable, directly using the detail points as graph nodes will cause large differences in the structure of finger vein graphs between classes, and image processing of finger vein images such as image enhancement may produce false detail points, affecting Accuracy of finger vein recognition, and the direct use of uniform block division me

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
  • Finger vein recognition method and device and storage medium
  • Finger vein recognition method and device and storage medium
  • Finger vein recognition method and device and storage medium

Examples

Experimental program
Comparison scheme
Effect test

no. 1 example

[0046] Such as figure 1 As shown, the first embodiment provides a finger vein recognition method, including steps S1-S3:

[0047] S1. Preprocessing the collected original finger vein image to obtain a preprocessed finger vein image.

[0048] S2. Obtain a node set from the preprocessed finger vein image according to the SLIC superpixel segmentation algorithm, and use the node set to construct a finger vein weighted map.

[0049] S3. Based on the improved graph convolutional neural network, perform finger vein recognition on the finger vein weighted graph, and obtain a recognition result.

[0050] As an example, in step S1, considering that there are areas with excessively large brightness changes in the collected original finger vein images, or noises such as areas with blurred texture details, the original finger vein images are preprocessed to obtain preprocessed finger vein images, such that Subsequently, the node set can be obtained from the preprocessed finger vein image...

no. 2 example

[0103] Based on the second embodiment of the first embodiment, an experiment was carried out using 10 single-modal original finger vein images collected from 100 different individuals and according to the finger vein recognition method described in the first embodiment.

[0104] The recognition system adopts 1:1 matching mode, and adopts ROC (Receiver Operating Characteristic, receiver operating characteristic) as the indicator of system performance evaluation, which has an important evaluation parameter, EER (Equal Error Rate, equal error rate), when the system The lower the EER, the fewer the number of false matches of the system, the better the classification effect of the corresponding test samples, and the better the performance of the recognition system.

[0105] The experimental environment uses Ubuntu64-bit operating system, the CPU is Inter(R) Core(TM) i5-8300H CPU, the main frequency is 2.30GHz, the memory is 8GB; the GPU is NVIDIA GeForce GTX 1050Ti, the programming ...

no. 3 example

[0126] Such as Figure 12 As shown, the second embodiment provides a finger vein recognition device, including: a finger vein image preprocessing module 21, which is used to preprocess the collected original finger vein image to obtain a preprocessed finger vein image; finger vein weighted map construction Module 22 is used to obtain a node set from the preprocessed finger vein image according to the SLIC superpixel segmentation algorithm, and uses the node set to construct a finger vein weighted map; the finger vein recognition module 23 is used to perform finger vein recognition based on the improved convolutional neural network. Finger vein recognition is performed on the vein weighted image, and the recognition result is obtained.

[0127] As an example, through the finger vein image preprocessing module 21, considering that there are areas with excessive brightness changes in the collected original finger vein images, or noise such as areas with blurred texture details, t...

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 finger vein recognition method and device and a storage medium. The finger vein recognition method comprises the following steps: preprocessing an acquired original finger vein image to obtain a preprocessed finger vein image; obtaining a node set from the preprocessed finger vein image according to an SLIC superpixel segmentation algorithm, and constructing a finger veinweighted graph by using the node set; and based on the improved graph convolutional neural network, performing finger vein recognition on the finger vein weighted graph to obtain a recognition result. The graph model of the finger vein image can be constructed by comprehensively considering the stability of the graph structure and the randomness of the finger vein image, and the finger vein recognition precision is improved.

Description

technical field [0001] The invention relates to the technical field of biometric identification, in particular to a finger vein identification method, device and storage medium. Background technique [0002] Finger vein recognition technology is a new biometric identification technology that is widely used in identity authentication. Its working principle is to extract the biological characteristics of finger veins from finger vein images, and compare the finger vein feature information with the pre-registered finger vein features. Compare to complete identity authentication. In order to make finger vein images better express the feature information of finger veins, finger vein recognition methods proposed in recent years mainly represent finger vein images as graph models, that is, directly select detail points from finger vein images as graph nodes, or evenly Divide the tiles to obtain the node set to build the graph model. But in fact, the detail points of finger veins ...

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): G06K9/00G06K9/32G06K9/34G06K9/46G06K9/52G06K9/62G06N3/04G06N3/08
CPCG06N3/08G06V40/10G06V40/14G06V10/25G06V10/267G06V10/44G06V10/431G06N3/048G06N3/045G06F18/241
Inventor 杨金锋李冉张海刚
Owner SHENZHEN POLYTECHNIC
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