Non-contact palm vein recognition method based on improved residual network

A recognition method, non-contact technology, applied in character and pattern recognition, biological feature recognition, biological neural network model, etc., can solve problems such as poor generalization ability and unsatisfactory recognition rate, and achieve increased multiplication coefficient, high The effect of recognition rate and robustness

Active Publication Date: 2021-01-08
TOP GLORY TECH INC CO LTD
View PDF14 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The technical problem to be solved by the present invention is to provide a non-contact palm vein recognition method based on the improved residual network, which overcomes the poor generalization ability caused by the large-angle rotation, translation and scaling of the non-contact collected vein images. , leading to the problem of unsatisfactory recognition rate

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-contact palm vein recognition method based on improved residual network
  • Non-contact palm vein recognition method based on improved residual network
  • Non-contact palm vein recognition method based on improved residual network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0046] Refer to attached figure 1 As shown, the present embodiment relates to a non-contact palm vein recognition method based on an improved residual network, comprising the following steps:

[0047] 1) Use non-contact equipment to collect two infrared images of the same palm, denoted as pic1 and pic2, the images are attached figure 2 As shown, the image size is: 1280 pixels * 720 pixels;

[0048] 2) Locate the ROI area of ​​the palm: Input the two infrared images pic1 and pic2 into the trained ROI detection deep learning model (denoted as model1) respectively, and obtain the corresponding ROI area position information respectively. According to the two infrared images pic1 and The ROI area information of pic2 cuts out the ROI images of two infrared images, refer to the attached image 3 As shown, the specific steps include:

[0049] 2.1) Use non-contact equipment to collect images containing 5000*10 palms, use the labelImage tool to manually label the ROI area of ​​​​th...

experiment example

[0079] Experiment 1: This experiment uses non-contact equipment to collect infrared normal palm vein images of 1,000 people within the range of [90, 120]mm from the camera. Each person collects 10 images of left and right palms in normal postures, totaling 20,000 images Infrared palm images, respectively apply the palm vein recognition method involved in Example 1 and the palm vein recognition model model3 involved in Comparative Example 1 to identify and verify; the verification method is: each type of palm is registered using the first infrared palm vein image, and the The remaining 9 images were verified by palm veins, and the pass rate was counted. The specific statistical results are shown in Table 1.

[0080] Experiment 2: Based on the left and right palm registration templates of 1000 people registered in Experiment 1, within the range of [90, 120] mm from the camera, and then collect infrared palm images randomly rotated within the angle range of [-45°, +45°], For eac...

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 relates to a non-contact palm vein recognition method based on an improved residual network. The non-contact palm vein recognition method comprises the following steps: 1) collecting twoinfrared images of the same palm; 2) positioning an ROI area of a palm; 3) carrying out palm vein registration; 4) carrying out palm vein verification; and 5) carrying out palm vein verification judgment: setting an identification threshold T, calculating the distance between the feature vector and the registration template, judging that palm vein verification succeeds if the distance is smallerthan the set identification threshold T, and otherwise, judging that verification fails. According to the improved residual network structure provided by the invention, texture features of different scales of an input sample can be extracted during training, so that the trained model has the capability of extracting multi-scale texture information, and the extracted feature vector better expressesthe information of the input sample; and various scaling and translation problems of an input sample can be solved to a certain extent.

Description

technical field [0001] The invention belongs to the technical field of biological feature recognition and deep learning, and in particular relates to a non-contact palm vein recognition method based on an improved residual network. Background technique [0002] Palm veins are biological characteristics that are not easy to be counterfeited in living organisms. They have rich, unique and stable identity information, unique advantages in security performance, and great market potential. The use of biometric features such as palm veins can be used for easy identification; however, the use of contact devices depends on the habit of using the palm in contact with the device, and the experience for first-time users is often poor; use of contact devices in public places , It will increase the risk of infectious diseases due to contact with equipment, and it will easily cause people's resistance when using it; therefore, it has become the general trend to replace traditional contact...

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): G06K9/00G06K9/32G06K9/46G06N3/04
CPCG06V40/10G06V40/14G06V10/25G06V10/44G06N3/045
Inventor 赵国栋朱晓芳李学双张烜
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