Fingerprint identification method combining point with line

A technology of fingerprint identification and dot-line, which is applied in the field of biometrics, can solve the problems of large influence of false feature points, poor anti-noise ability, and easy to cause misjudgment, etc., to reduce the influence of false feature points, strong anti-noise ability, The effect of improving reliability

Inactive Publication Date: 2008-12-24
HARBIN INST OF TECH
View PDF0 Cites 26 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The present invention solves the problems of the existing point-matching fingerprint recognition method, which is easy to cause misjudgment, is greatly affected by false feature points, has poor an...

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
  • Fingerprint identification method combining point with line

Examples

Experimental program
Comparison scheme
Effect test

specific Embodiment approach 1

[0016] Specific implementation mode one: see figure 1 , this embodiment consists of the following steps:

[0017] Step A1, in the database image T p , taking the database image T p The center point of is the center of the circle, the circular area with R as the radius and the image to be recognized T q Look for matching points in the corresponding area in , wherein R represents a real number greater than zero, and the selection of the R value should ensure that there are three to five feature points in the circular area. According to the database image T p Each feature point in the circular area, in the image to be recognized T q Traverse all the points in the circular area to select a point that matches the feature point, and the two points are collectively recorded as a pair of matching points;

[0018] Step A2, sorting the pairs of matching points obtained in step A1 according to matching similarity, and selecting N pairs of matching points with higher matching similari...

specific Embodiment approach 2

[0025] Specific implementation mode two: this implementation mode further illustrates on the basis of specific implementation mode one that the specific method for sorting the matching points according to the matching similarity described in step A1 is:

[0026] Step B1, comparing the database image T p and the image to be recognized T q Four feature quantities of two feature points in the circular area in : feature point type, distance from feature point to center of circle, frequency at feature point and difference between feature point orientation angle and circle center orientation angle, use P={ P 1 ,P 2 ...P N}, Q={Q 1 , Q 2 ...Q N} respectively represent the database image T p and the image to be recognized T q A collection of feature points in the circular area;

[0027] Step B2, select a feature point P in the set P i , to traverse all the feature points in the set Q, for any feature point Q in the set Q j , respectively judge the feature point P i with Q ...

specific Embodiment approach 3

[0033] Specific implementation mode three: This implementation mode further illustrates on the basis of specific implementation mode one that the specific method of sorting the feature points described in step A2 according to similarity is:

[0034] Step C1, calculate each pair of matching points P i and Q j The frequency difference Δf, the feature point P i and Q j The distance difference to their respective centers (d i -d j ) and the feature point P i and Q j The difference of the direction angle of (θ i -θ p )-(θ j -θ q );

[0035] Step C2, find the largest frequency difference max|Δf| and the largest distance difference max|d among N pairs of matching points i -d j The difference between | and the maximum direction angle max|(θ i -θ p )-(θ j -θ q )|;

[0036] Step C3, according to the parameters obtained in step C2 by the formula |Δf / maxΔf|+|(d i -d j ) / max(d i -d j )|+|[(θ i -θ p )-(θ j -θ q )] / max[(θ i -θ p )-(θ j -θ q )]|Obtain the similari...

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 fingerprint identification method by using the joint of lines and points, which relates to a fingerprint identification method by using the joint of lines and points so as to solve the problems that the existing fingerprint identification method using dot matching easily leads to wrong identification, is greatly affected by fake characteristic points and has relatively poor noise immunity, and the fingerprint identification method using line matching has relatively large calculation work and low identification speed. All matching points in a database image Tp and an image Tq to be identified are selected; sorting is carried out to a plurality of obtained matched points according to matching similarity, and N pairs of matching points with the highest matching similarity are selected; K pairs of matched points are selected from the N pairs of matched points to serve as reference points; the difference between the X-axis and Y-axis and a direction angle is obtained to serve as the offset of two images; translation and rotation transformation are carried out to the image Tq; after correction, the ridge lines of the image Tq and the image Tp mutually match; the matched number is recorded; if the length weighted average value of all matched ridge lines meets a threshold value, the image Tp is identified to match with the image Tq; otherwise, the image Tp is identified not to match with the image Tq.

Description

technical field [0001] The invention relates to a fingerprint identification method, in particular to a fingerprint identification method combining dots and lines, which belongs to the field of biological identification. Background technique [0002] Fingerprint recognition is a biometric technology that uses the uniqueness and stability of fingerprint images to compare two fingerprint images to determine whether they come from the same finger. The so-called uniqueness means that the fingerprints of different people are different, and the fingerprint images of different fingers of the same person are also different; the so-called stability means that the fingerprint of a person basically does not change greatly. [0003] At present, the commonly used fingerprint identification method is to simply use the feature points of the fingerprint image to match, and judge whether the two images are from the same finger according to the number of detail feature point pairs that meet t...

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): G06K9/00
Inventor 王明江闫志锋王进祥韦秋初董颖杰刘钊刘鹏和王峰彭刚桑坚张永胜张国君肖永生马晓卫
Owner HARBIN INST OF TECH
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

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap