Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Finger three-mode fusion recognition method and device based on crystal diagram structure

A fusion recognition, three-modal technology, applied in the field of biometrics, can solve the problems of affecting recognition accuracy and stability, not taking into account the multi-modal relationship of fingers, poor fusion effect, etc., to improve recognition accuracy and stability. Effect

Pending Publication Date: 2020-11-20
SHENZHEN POLYTECHNIC
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, in practical applications, only relying on single-mode finger authentication, the recognition accuracy and stability are low
In recent years, although a finger multi-modal fusion recognition method based on a deep neural network has been proposed, the fusion method used is relatively single, and the relationship between multi-modal fingers is not considered, resulting in poor fusion results and affecting recognition accuracy. and stability

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 three-mode fusion recognition method and device based on crystal diagram structure
  • Finger three-mode fusion recognition method and device based on crystal diagram structure
  • Finger three-mode fusion recognition method and device based on crystal diagram structure

Examples

Experimental program
Comparison scheme
Effect test

no. 1 example

[0044] Such as Figure 1-2 As shown, the first embodiment provides a finger three-modal fusion recognition method based on crystal graph structure, including steps S1-S3:

[0045] S1. Respectively perform structural expression on the acquired fingerprint feature image, finger vein feature image and knuckle pattern feature image to obtain a first feature map, a second feature map and a third feature map.

[0046] S2. According to the first feature map, the second feature map and the third feature map, construct a three-mode crystal map of the finger.

[0047] S3. Input the trimodal crystal graph of the finger into the recognition model based on the graph convolutional neural network to obtain the recognition result.

[0048]In this embodiment, the first feature map, the second feature map, and the third feature map are obtained by structurally expressing the acquired fingerprint feature image, finger vein feature image, and knuckle pattern feature image respectively, so as to ...

no. 2 example

[0079] Such as Image 6 As shown, the second embodiment provides a finger three-modal fusion recognition device based on a crystal graph structure, including: a finger three-modal feature map acquisition module 21, which is used to separately acquire fingerprint feature images, finger vein feature images, and finger vein feature images. The knuckle print feature image is structured to obtain the first feature map, the second feature map and the third feature map; the finger trimodal crystal map construction module 22 is used to obtain the first feature map, the second feature map and the third feature map. The three-feature map is used to construct the tri-modal crystal map of the finger; the tri-modal finger recognition module 23 is used to input the tri-modal crystal map of the finger into the recognition model established based on the graph convolutional neural network to obtain the recognition result.

[0080]In this embodiment, through the acquisition module 21 of the thr...

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 three-mode fusion recognition method and device based on a crystal diagram structure. The finger three-mode fusion recognition method based on the crystal diagram structure comprises the steps: carrying out structural expression on an obtained fingerprint feature image, an obtained finger vein feature image and an obtained knuckle line feature image, and obtaininga first feature diagram, a second feature diagram and a third feature diagram; constructing a finger three-mode crystal diagram according to the first feature diagram, the second feature diagram and the third feature diagram; and inputting the finger three-mode crystal diagram into an identification model established based on a graph convolutional neural network to obtain an identification result.According to the method, the finger three-mode feature images can be effectively fused by considering the relationship among the finger three modes, and the finger three-mode recognition is carried out based on the recognition model constructed by the graph convolutional neural network, so that the finger three-mode recognition precision and stability are improved.

Description

technical field [0001] The invention relates to the technical field of biometrics, in particular to a method and device for three-mode fusion recognition of fingers based on a crystal graph structure. Background technique [0002] With the development of information and science and technology, biometric technology is widely used for identity authentication. Human hands contain fingerprints, finger veins, knuckle prints, palm prints, hand shapes, finger shapes, palm veins, and dorsal hand veins, among which the three modes of fingerprints, finger veins, and knuckle Can achieve identity authentication. However, in practical applications, only relying on the single-mode of the finger for identity authentication, the recognition accuracy and stability are low. In recent years, although a finger multi-modal fusion recognition method based on a deep neural network has been proposed, the fusion method used is relatively single, and the relationship between multi-modal fingers is ...

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): G06K9/00G06K9/46G06K9/62G06N3/04G06N3/08
CPCG06N3/08G06V40/1347G06V40/13G06V40/1365G06V40/70G06V40/14G06V10/44G06N3/045G06F18/241G06F18/254Y02T10/40
Inventor 师一华杨金锋张海刚赵子豪
Owner SHENZHEN POLYTECHNIC
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products