Federal learning-based finger vein and palm vein recognition method

A recognition method, finger vein technology, applied in the field of palm vein recognition, can solve the problems of privacy data leakage, non-independent and identical distribution of data sets, etc., to reduce the risk of leakage and solve the effects of non-independent and identical distribution

Active Publication Date: 2022-08-05
广州脉泽科技有限公司 +1
View PDF19 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0007] The present invention provides a method, system and computer-readable storage medium for identifying finger veins and palm veins based on federated learning, which reduces the need for multiple data parties to conduct cooperative training The risk of private data leakage, and solve the problem of non-independent and identical distribution between data sets

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
  • Federal learning-based finger vein and palm vein recognition method
  • Federal learning-based finger vein and palm vein recognition method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0042] like figure 1 As shown in the figure, a method for identifying finger vein and palm vein based on federated learning is characterized in that, it includes the following steps:

[0043] S1. Obtain a hand vein image;

[0044] It should be noted that obtaining the hand vein image in the present invention includes: using an infrared camera to obtain the original finger vein grayscale image and the original palm vein grayscale image respectively. It should be noted that in a specific application scenario, it may be for The identification of finger veins can also be aimed at the identification of palm veins (such as palm), or the identification of hand veins in the hand composed of fingers and palms (palm). application scenarios require.

[0045] S2. Use public datasets to perform federated learning training on the mobilenetV2 detection model;

[0046]It should be noted that in the federated learning training of the mobilenetV2 detection model, the convolutional part of th...

Embodiment 2

[0070] like figure 2 As shown, the second aspect of the present invention provides a system for identifying finger and palm veins based on federated learning, the system comprising: a memory and a processor, wherein the memory includes a federated learning-based finger vein and palm vein identification system A method program, when the method program for identifying finger vein and palm vein based on federated learning is executed by the processor, the following steps are implemented:

[0071] S1. Obtain a hand vein image;

[0072] It should be noted that obtaining the hand vein image in the present invention includes: using an infrared camera to obtain the original finger vein grayscale image and the original palm vein grayscale image respectively. It should be noted that in a specific application scenario, it may be for The identification of finger veins can also be aimed at the identification of palm veins (such as palm), or the identification of hand veins in the hand co...

Embodiment 3

[0098] A third aspect of the present invention provides a computer-readable storage medium, the computer-readable storage medium includes a federated learning-based finger vein and palm vein identification method program, and the federated learning-based finger vein and palm vein identification method When the program is executed by the processor, it implements the steps of the method for identifying finger vein and palm vein based on federated learning.

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 federal learning-based finger vein and palm vein recognition method and system and a computer readable storage medium. The method comprises the following steps of obtaining a hand vein image; carrying out federated learning training on the mobilenetV2 detection model by utilizing the public data set; the model parameters of the convolution part of the trained vein detection model mobilenetV2 are uploaded to a center party; the central party performs federal learning aggregation to obtain a plurality of aggregation models; performing fine tuning on the obtained aggregation model in a local data set to obtain a trained mobileNetV2 detection model; inputting the hand vein image into a trained mobileNetV2 detection model to extract a feature vector; and calculating the similarity between the extracted feature vector and a vein feature vector of a registered person in a preset database, and if the similarity is greater than a preset threshold, determining that the current hand vein image belongs to the registered person, and successfully identifying. According to the invention, the risk of privacy data leakage is reduced; and meanwhile, the problem of non-independent identically distributed data sets is solved.

Description

technical field [0001] The present invention relates to the technical field of palm vein identification, and more particularly, to a method, system and computer-readable storage medium for identifying finger vein and palm vein based on federated learning. Background technique [0002] Vein identification is an emerging biometric identification technology, which includes finger vein identification and palm vein identification. It uses images of vein distribution in palms or fingers for identification. This technology is based on the fact that the blood flowing in the human hand can absorb near-infrared light of a specific wavelength. When the near-infrared light irradiates the hand, a part of it is absorbed by the deoxyhemoglobin in the blood, so that the vein pattern appears dark shadow in the image. Other non-vein areas exhibit higher brightness, resulting in clear images of finger or palm veins. [0003] However, at present, the application of finger vein and palm vein r...

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): G06V40/14G06V10/44G06V10/764G06V10/82G06V10/74G06K9/62G06N3/04G06N3/08G06N20/00
CPCG06V40/14G06V10/44G06V10/764G06V10/82G06V10/74G06N3/08G06N20/00G06N3/045G06F18/22G06F18/241
Inventor 董延杰康文雄连枫钊黄俊端曾香玉
Owner 广州脉泽科技有限公司
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