Eureka AIR delivers breakthrough ideas for toughest innovation challenges, trusted by R&D personnel around the world.

Finger vein recognition method, apparatus and device

A recognition method, finger vein technology, applied in biometric recognition, character and pattern recognition, instruments, etc., can solve the problems of reduced recognition accuracy, reduced recognition speed, and large time consumption, so as to reduce the number of comparisons and ensure accuracy rate and speed, which is conducive to the effect of accurate comparison

Active Publication Date: 2019-01-08
GRG BAKING EQUIP CO LTD
View PDF9 Cites 8 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] Among them, when the identity of the measured object is identified among N registered users for 1:N matching, the recognition rate drops seriously as the magnitude of N increases, and the recognition accuracy also decreases; while the current information and the database When comparing all the template information in 1:1 cycle one by one, if the magnitude of N is too large, it will consume a lot of time, that is, the recognition speed will decrease accordingly.

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, apparatus and device
  • Finger vein recognition method, apparatus and device
  • Finger vein recognition method, apparatus and device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0056] This embodiment proposes a finger vein identification method, please refer tofigure 1 , figure 1 This is a flowchart of the finger vein identification method provided in this embodiment; the method may include:

[0057] Step s110: Divide the received image to be matched into blocks to obtain several image blocks.

[0058] The received image to be matched may be divided into uniform blocks to facilitate subsequent feature extraction and splicing. This embodiment takes uniform division as an example.

[0059] It should be noted that the image to be matched before the block is a preprocessed image, and the process of preprocessing is not limited here. You can refer to the existing preprocessing process. For example, you can extract the ROI area of ​​the collected biometric image, Angle correction, grayscale adjustment and size normalization, etc.

[0060] Step s120, perform SIFT feature extraction on several image blocks to obtain SIFT feature values ​​of each image bloc...

Embodiment 2

[0085] The above embodiment does not limit the selection rules of candidate classes. In this embodiment, the overall identification process is introduced by taking the distance between the image to be matched and each cluster center as the candidate class selection condition as an example, which mainly includes the following steps:

[0086] The image to be matched is divided into 4 blocks on average, and SIFT features are extracted from each image block to obtain the SIFT feature values ​​of the 4 image blocks.

[0087] Calculate the distance of 4 SIFT eigenvalue features to 10 class centers in the image library.

[0088] The class with the smallest distance between each image block and the 10 class centers is: the class with the smallest distance of image block 1 is the first class, the class with the smallest distance of image block 2 is the second class, and the class with the smallest distance of image block 3 is the first class The class with the smallest distance between i...

Embodiment 3

[0091] Based on the above embodiment, since the similarity between each image block and the cluster center may be calculated, there may be a large gap between the possible matching classes of each image block, and there may be more candidate classes obtained by simply analyzing and screening the distance of each image block. , the error is relatively large, in order to improve the accuracy, preferably, the screening of candidate classes may specifically include the following steps:

[0092] Step 1: Calculate the distance between each image block and each cluster center to determine the category of each image block;

[0093] Step 2: Encode each image block according to the category label of the category to which it belongs;

[0094] Step 3: Counting the coding of each image block in the image to be matched according to the image block splitting rule, and using the statistical result as the feature code of the image to be matched;

[0095] Step 4: Perform feature code matching ...

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 identification method, which relates to the field of biometric identification. The method comprises the following steps: the received image to be matched is divided into blocks to obtain an image block; the SIFT eigenvalues of each image block are obtained by extracting the SIFT eigenvalues of several image blocks; according to the SIFT eigenvalue of each image block, the similarity between each image block and each cluster center in the image library is calculated, and the distance value corresponding to each cluster center is obtained, wherein the clustering center is the feature center of all kinds of image blocks of template image in the image library; candidates of clustering centers are selected according to the distance value; the image to be matched is compared with each image in the candidate class one by one, and the recognition result is obtained according to the comparison result. This method can match finger vein image quickly and accurately, and improve the efficiency of finger vein recognition. The invention also discloses a finger vein identification apparatus and device, which have the beneficial effects.

Description

technical field [0001] The present invention relates to the field of biometric identification, in particular to a finger vein identification method, device and equipment. Background technique [0002] Biometric recognition technology is a technology that recognizes the human body based on the inherent physiological or behavioral characteristics of human beings and computer information systems, such as palmprint recognition, signature recognition, fingerprint recognition, finger vein recognition, iris recognition, etc. Because finger veins are congenital, invariant and unique, they are widely used in authentication equipment in the public domain, such as membership identification all-in-one machines, bank ATM machines, access control management systems, PC login, instead of car locks, safe management, copier management, Electronic payment and other links that require personal identification and authentication. [0003] Before finger vein recognition, the user needs to regist...

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): G06K9/00G06K9/46G06K9/62
CPCG06V40/10G06V40/14G06V10/462G06F18/22G06F18/23
Inventor 王丹丹王晓亮陈良旭
Owner GRG BAKING EQUIP 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
Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com