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

Rapid fingerprint identification method

A fingerprint identification and fingerprint technology, which is applied in the field of fingerprint identification, can solve the problems of less calculation, lower identification performance, fingerprint offset and sensitivity to direction rotation changes, etc., to achieve simple matching, improved identification performance, lower reference point position and The effect of the influence of its direction error

Inactive Publication Date: 2009-12-23
NANJING UNIV OF SCI & TECH
View PDF0 Cites 35 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

This type of method requires less calculation and is easy to match. It can still extract features for matching for poor-quality fingerprints, but this type of method is sensitive to fingerprint offset and direction rotation changes, resulting in reduced recognition performance.

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
  • Rapid fingerprint identification method
  • Rapid fingerprint identification method
  • Rapid fingerprint identification method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0022] combine figure 1 , the present invention is based on the fast fingerprint identification method of image feature and minutiae feature, and the steps are as follows:

[0023] In the first step, after performing image distortion correction and image segmentation on the input image, the direction field is smoothed according to the consistency of the gradient direction in different scale windows, and the reference point of the fingerprint is detected by using the attribute of multi-resolution window direction change, followed by Taking the reference point as the center, observe the difference between the direction of the fingerprint and the radial direction in the fan-shaped area of ​​different scales to determine the reference direction of the reference point, that is, the reference point detection and its direction determination, that is, the fingerprint image is preprocessed, including distortion rectification, segmentation, etc. steps, and then divide the image into non...

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 rapid fingerprint identification method based on image characteristics and minutia characteristics. The method comprises the following steps: firstly, detecting a reference point and determining a direction thereof, and determining the reference direction of the reference point by observing the difference between the fingerprint direction and the radial direction in sector regions with different sizes; carrying out image characteristic extraction, performing feature selection after normalization, and finally, obtaining the characteristic vector of the fingerprint image; establishing a minutia template and transforming the obtained minutiae under a polar coordinate system to establish a fingerprint minutia template; and carrying out the characteristic matching, i.e. as for the input fingerprints to be compared, judging whether the two fingerprints are matched or nor by using the fingerprint image characteristics and the minutia template obtained from the three steps. The invention not only can effectively inhibit the influence generated during the fingerprint image translation and the rotation, but also avoids the dependence to the detected reference point and the direction thereof in the recognition process and can also rapidly and accurately judge whether the fingerprint to be identified is matched with the template fingerprint or not.

Description

technical field [0001] The invention belongs to fingerprint recognition technology, in particular to a fast fingerprint recognition method based on image features and minutiae features. Background technique [0002] Among many biometric identification systems, fingerprint identification systems are more and more popular due to their advantages of small size, low cost, easy operation, and high reliability. Correspondingly, the market demand for products based on fingerprint identification technology is expanding day by day. The application is also more and more extensive. [0003] Fingerprinting is the process of comparing two fingerprints to determine if they are from the same finger. Fingerprint recognition technology mainly involves steps such as fingerprint image acquisition, fingerprint image processing, feature extraction, data saving, comparison and matching of feature values. Among them, feature extraction and matching of fingerprint images are two key issues in the...

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): G06K9/00
Inventor 曹国孙权森夏德深
Owner NANJING UNIV OF SCI & TECH
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