Unlock instant, AI-driven research and patent intelligence for your innovation.

Finger vein recognition method based on deep correlation feature learning

A technology of related features and identification methods, applied in character and pattern recognition, acquisition/organization of fingerprints/palmprints, instruments, etc., can solve problems such as the lack of a good solution to the axial rotational deformation of fingers, and achieves improved success rate, resistance to The effect of increased rotation ability

Pending Publication Date: 2022-02-18
安徽澄小光智能科技有限公司
View PDF0 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Although the existing finger vein feature algorithm has achieved high recognition accuracy, there is still no good solution to the problem of finger axial rotation deformation

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 based on deep correlation feature learning
  • Finger vein recognition method based on deep correlation feature learning
  • Finger vein recognition method based on deep correlation feature learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0048] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only some, not all, embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without creative efforts fall within the protection scope of the present invention.

[0049] see figure 1 , the present invention is a kind of finger vein recognition method based on deep correlation feature learning, comprising the following steps:

[0050] Step 1: collect the finger vein image and perform ROI interception on the image; the collection of the finger vein image in this embodiment can be divided into three categories: projection imaging, side projection imaging and reflection imaging; since the original finger vein image contains angl...

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 based on deep correlation feature learning, and relates to the technical field of finger vein recognition. The method comprises the following steps: step 1, acquiring a finger vein image and carrying out ROI (Region of Interest) interception on the image; 2, performing finger axial rotation correction on the intercepted image, and performing special fusion; step 3, performing feature extraction on the finger shape; and step 4, matching the texture features of the finger shape. Therefore, the overall anti-rotation capability is further improved, and the overall anti-rotation capability is further improved.

Description

technical field [0001] The invention belongs to the technical field of finger vein recognition, in particular to a finger vein recognition method based on deep correlation feature learning. Background technique [0002] At present, finger vein recognition has attracted more and more attention due to its unique security and portability, and more and more finger vein recognition algorithms have been proposed one after another. The conventional finger vein recognition system is mainly divided into four steps: image acquisition, image preprocessing, feature extraction and matching. [0003] The method based on deep correlation feature learning is to autonomously learn vein features through neural network for identity recognition, which can achieve high recognition accuracy. Matching refers to the measurement of two feature vectors to calculate the similarity between them. Among them, feature extraction is a crucial step, which directly affects the subsequent matching similarit...

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): G06V40/12G06V10/25G06V10/44G06V10/74G06V10/764G06V10/774G06V10/80G06K9/62
CPCG06F18/22G06F18/2411G06F18/253G06F18/214
Inventor 洪伟管一鸣程勇史寿增梅列汝
Owner 安徽澄小光智能科技有限公司