A finger vein recognition method and device based on attribute learning

A technology of attribute learning and finger veins, applied in biometric recognition, character and pattern recognition, instruments, etc., to enhance the ability of intuitive expression, explain the meaning well, and improve the efficiency of storage and calculation

Active Publication Date: 2020-04-17
SHANDONG UNIV OF FINANCE & ECONOMICS
View PDF7 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0009] In view of the deficiencies in the existing technology, solve the problem of how to intuitively represent the features in the finger vein recognition in the existing technology, improve the partition between the features in the finger vein recognition, and how to improve the finger vein recognition In view of the problems of recognition accuracy and recognition efficiency, the present invention provides a method and device for finger vein recognition based on attribute learning. Compared with the features extracted in traditional finger vein recognition, the present invention effectively improves the accuracy of features in existing finger vein recognition. Interpretability and partitioning between image features can effectively improve the recognition accuracy and recognition efficiency of finger vein recognition

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
  • A finger vein recognition method and device based on attribute learning
  • A finger vein recognition method and device based on attribute learning
  • A finger vein recognition method and device based on attribute learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0066] The purpose of Embodiment 1 is to provide a method for recognizing finger veins based on attribute learning.

[0067] In order to achieve the above object, the present invention adopts the following technical scheme:

[0068] Such as figure 1 as shown,

[0069] A method for recognizing finger veins based on attribute learning, the method comprising:

[0070] Obtain the finger vein image library, and perform data augmentation to form a training set;

[0071] Preset the interpretability attribute and distinguishing attribute corresponding to the finger vein image, and establish its corresponding attribute learning model for each interpretable attribute and distinguishing attribute in the training set;

[0072] Obtain the finger vein image to be recognized, determine the attribute characteristics of the finger vein image to be recognized according to all attribute learning models, and perform finger vein recognition.

[0073] In this embodiment, a finger vein recogniti...

Embodiment 2

[0126] The purpose of Embodiment 2 is to provide a computer-readable storage medium.

[0127] In order to achieve the above object, the present invention adopts the following technical scheme:

[0128] A computer-readable storage medium, in which a plurality of instructions are stored, and the instructions are adapted to be loaded by a processor of a terminal device and perform the following processing:

[0129] Obtain the finger vein image library, and perform data augmentation to form a training set;

[0130] Preset the interpretability attribute and distinguishing attribute corresponding to the finger vein image, and establish its corresponding attribute learning model for each interpretable attribute and distinguishing attribute in the training set;

[0131] Obtain the finger vein image to be recognized, determine the attribute characteristics of the finger vein image to be recognized according to all attribute learning models, and perform finger vein recognition.

[013...

Embodiment 3

[0134] The purpose of Embodiment 3 is to provide a finger vein recognition device based on attribute learning.

[0135] In order to achieve the above object, the present invention adopts the following technical scheme:

[0136] A finger vein recognition device based on attribute learning, using an Internet terminal device, including a processor and a computer-readable storage medium, the processor is used to implement instructions; the computer-readable storage medium is used to store multiple instructions, and the instructions is adapted to be loaded by the processor and perform the following processing:

[0137] Obtain the finger vein image library, and perform data augmentation to form a training set;

[0138] Preset the interpretability attribute and distinguishing attribute corresponding to the finger vein image, and establish its corresponding attribute learning model for each interpretable attribute and distinguishing attribute in the training set;

[0139] Acquire th...

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 based on attribute learning. The method includes: acquiring a finger vein image database, performing data augmentation to form a training set; designing interpretable attributes according to the characteristics of finger veins, and separately For each interpretability attribute, a corresponding attribute learning model is established to obtain the value of the interpretability attribute; in order to further improve the discrimination of features, a convolutional neural network based on a discriminative auxiliary branch is proposed as the learning of discriminative attributes model, and design a new Inter-intra loss function to enhance the discrimination of the discriminative attribute learning model; obtain the image to be recognized, and determine the attribute characteristics of the image to be recognized according to the entire attribute learning model, and perform finger vein recognition. Compared with traditional features, the method proposed by the present invention improves the interpretability, recognition accuracy and recognition efficiency of existing features.

Description

technical field [0001] The invention belongs to the technical field of finger vein recognition, and relates to a finger vein recognition method and device based on attribute learning, in particular to a finger vein recognition method and device based on interpretable attribute learning and distinguishable attribute learning. Background technique [0002] In recent years, biometrics has played an increasingly important role in information security, e-commerce and other fields. As an emerging biological feature, finger veins have attracted more and more attention from researchers. Compared with more mature biological features such as fingerprints and faces, finger veins have the advantages of internal features, living body recognition, non-contact acquisition, and acquisition equipment with small size and low cost. In view of these advantages of finger veins, finger vein recognition technology has been widely used in attendance, car locks, ATM and other fields. [0003] Trad...

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): G06K9/00G06K9/62G06K9/66G06N3/04
CPCG06V40/10G06V40/14G06V30/194G06N3/045G06F18/214
Inventor 袭肖明尹义龙孟宪静杨璐
Owner SHANDONG UNIV OF FINANCE & ECONOMICS
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