Method for enhancing fingerprint image recognition

A fingerprint image and fingerprint technology, which is applied in the field of enhanced fingerprint image recognition, can solve problems such as high system misrecognition rate and rejection rate, immature fingerprint classification method, and difficult definition matching degree of fingerprint image quantification

Inactive Publication Date: 2017-05-31
BEIHAI HESI TECH
View PDF5 Cites 8 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

For example, there is a lack of reliable detailed feature extraction methods, and it is still difficult to quantitatively define the matching degree in the compared fingerprint images. Immature fingerprint classification methods, for very blurred fingerprint images caused by sweating, swelling or moulting, the system Misrecognition rate and rejection rate are high, etc.

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
  • Method for enhancing fingerprint image recognition
  • Method for enhancing fingerprint image recognition
  • Method for enhancing fingerprint image recognition

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0021] A method for enhancing fingerprint image recognition, comprising: (1) utilizing a Gabor filter to realize enhancement of the fingerprint image; (2) grayscale variance, variance gradient, gradient modulus and low grayscale pixels of the fingerprint grayscale image (3) Introduce the linear combination feature of variance and gradient modulus, select the appropriate threshold value according to the relationship between this feature and the mean value, and initially distinguish the foreground area and background area of ​​the fingerprint; (4) Use mathematical morphology Opening and closing operations are used for post-segmentation processing to obtain accurate and complete fingerprint foreground areas.

[0022] The image enhancement method is: (1) divide the fingerprint image into blocks and extract the local spectral information of each block through windowed Fourier transform; (2) filter the transformed spectrum with a corresponding Gabor filter; (3) ) using inverse Fouri...

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

Provided is a method for enhancing fingerprint image recognition. The method includes following steps: (1) enhancing a fingerprint image by employing a Gabor filter; (2) calculating the grayscale variance, the variance gradient, the gradient modulus, and the pixel number of the low grayscale grade of a fingerprint grayscale image; (3) introducing a linear combination characteristic of the variance and the gradient modules, selecting a proper threshold according to the relation between the characteristic and a mean value, and preliminarily distinguishing a foreground area and a background area of a fingerprint; and (4) performing segmented processing by employing open-close operation in mathematical morphology to obtain the accurate and complete fingerprint foreground area. According to the method, the fingerprint image is enhanced by employing the Gabor filter, the node relation representation method in a curve coordinate system is finally proposed, the advantages of simple algorithm and fast calculating speed of the variance method are fully utilized, the defect that the method is easily influenced by noise is overcome, and more accurate fingerprint segmentation image is obtained.

Description

technical field [0001] The invention belongs to the technical field of fingerprint identification, and in particular relates to a method for enhancing fingerprint image identification. Background technique [0002] Fingerprint refers to the pattern composed of ridges and valleys on the surface of fingertips. Everyone has a unique fingerprint. The uniqueness of fingerprints is uniquely determined by the characteristics of local ridges and the relationship between them. The most commonly used method at present is to use the fingerprint minutiae (feature point) model proposed by the FBI to do minutiae matching, which uses the terminal points and bifurcation points of the fingerprint ridge line to identify fingerprints. By representing minutiae points as point patterns, an automatic fingerprint recognition problem is transformed into a special point pattern matching problem. What is recorded in the automatic fingerprint identification system is not the entire fingerprint image,...

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): G06K9/00G06T5/10G06T7/155G06T7/194
CPCG06T5/10G06T2207/20024G06V40/1347
Inventor 贺灿炎
Owner BEIHAI HESI 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