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

MCM method for fast matching and identification of finger veins

A finger vein, fast technology, applied in matching and classification, character and pattern recognition, acquisition/organization of fingerprints/palmprints, etc., can solve the problems of long recognition process, user scale limitation, etc., to reduce the capacity of registration template library , the effect of reducing time overhead and reducing storage requirements

Active Publication Date: 2021-11-23
TIANJIN UNIV
View PDF7 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the one-to-many identification method has a large limit on the scale of users and the identification process takes a long time.

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
  • MCM method for fast matching and identification of finger veins
  • MCM method for fast matching and identification of finger veins
  • MCM method for fast matching and identification of finger veins

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0051] In order to solve the above problems, the present invention provides a multiscale compression matching (Multiscale Compression Matching, MCM) method for quickly matching and identifying finger veins. In the process of image compression, the encryption algorithm is combined, and matching and identification can be performed without decryption, reducing the need for decryption. Matching template capacity and protecting template information, while protecting user privacy, greatly reduces the amount of calculation in subsequent processing and improves matching speed. The specific technical scheme involves three parts: image encryption, multi-scale compression and fast retrieval strategy. Firstly, the vein feature registration template after preprocessing and feature extraction is encrypted and compressed, and a small-capacity encrypted registration template library is established. When matching and identifying, the template to be identified is encrypted and compressed first,...

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 belongs to the field of biological feature identification and aims to provide a fast matching identification method. For this reason, the present invention, the MCM method that is used for fast matching identification finger vein, comprises image encryption, multi-scale compression and fast retrieval strategy three parts; Encryption and compression to establish a small-capacity encrypted registration template library; multi-scale compression specifically refers to: image compression is performed on the entire registration template library with different compression scales, the compressed registration template library is obtained, and the templates to be identified are compressed on the same scale before matching. Then perform pixel overlap rate matching with the entire registered template library to obtain the equal error rate (EER) curve and the minimum EER value under each compression scale, and obtain the actual cost of a single template to be identified completely matched. The present invention is mainly applied to the occasion of biometric identification.

Description

technical field [0001] The invention belongs to the field of biometric identification, in particular to a method for fast matching and identification of finger veins Background technique [0002] As a new biometric identification method, finger vein recognition technology has advantages in uniqueness, stability, portability and liveness detection compared with other biometric identification technologies such as fingerprint recognition, iris recognition, palmprint recognition, and face recognition. More prominent features, its development space and application prospects are also relatively broad. [0003] Finger vein feature, as an inherent identity feature of a person, has high immutability and immutability. Once lost and used by criminals for other purposes, there will be a great risk. Therefore, it is particularly important to protect the privacy of the vein feature template. . Most of the existing finger vein matching recognition methods focus on the improvement of reco...

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): G06K9/00
CPCG06V40/1365
Inventor 路志英李敏丁姝萌张建峰
Owner TIANJIN UNIV