Fingerprint recognition pretreatment method and device

A preprocessing device and a technology for fingerprint identification, applied in the field of biometric identification, can solve the problems of poor fingerprint image quality and practical application limitations of fingerprint identification, and achieve the effects of improving quality, improving accuracy and identification speed, and broadening the scope of application.

Inactive Publication Date: 2011-03-30
BEIJING YICHUANG TECH
View PDF0 Cites 17 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] At present, although important progress has been made in the research and development of fingerprint recognition preprocessing, and many applications have been obtained, due to the influence of high-frequency noise and other factors, the quality of fingerprint images is poor, and the quality of fingerprint images has a great impact on the accuracy of fingerprint recognition. And the performance of recognition speed has a very important impact, the poor quality of fingerprint image makes the practical application of fingerprint recognition subject to many restrictions

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 recognition pretreatment method and device
  • Fingerprint recognition pretreatment method and device
  • Fingerprint recognition pretreatment method and device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0055] refer to figure 1 , is a flowchart of a fingerprint recognition preprocessing method described in this embodiment.

[0056] S101, wavelet transform of the fingerprint image;

[0057]Wavelet transform is a new field of rapid development in mathematics at present, and it has dual meanings of profound theory and wide application at the same time. Wavelet transform is an inversion formula established through physical intuition and actual needs of signal processing experience. It is a time and frequency local domain transform. It has a wide range of application fields. Noise, compression, transmission, identification, decontamination, etc.

[0058] The choice of wavelet base is very important when performing wavelet transform. On the one hand, because wavelet transform provides a variety of wavelet bases with different time-frequency characteristics, the selection of wavelet bases is diverse; on the other hand, in actual work, wavelet The converted wavelet coefficient is ...

Embodiment 2

[0126] For the above method embodiments, the present invention also provides corresponding device embodiments.

[0127] refer to Figure 14 , which is a structural diagram of a fingerprint recognition preprocessing device according to this embodiment, and the fingerprint recognition preprocessing device includes:

[0128] A wavelet transform unit 1401, configured to perform wavelet transform on the collected fingerprint image to obtain a low-frequency image;

[0129] The ridge direction estimation unit 1402 is used for estimating the ridge direction on the low-frequency image obtained by the wavelet transform unit, and obtaining the fingerprint image direction map;

[0130] The direction filtering unit 1403 is used to select a direction filter template to perform direction filtering on the obtained fingerprint image direction map.

[0131] Preferably, the fingerprint recognition preprocessing device further includes:

[0132] Thinning unit 1404, configured to perform horizo...

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 provides fingerprint recognition pretreatment method and device. The method comprises the following steps that: fingerprint images with little information content and compactness in high frequency images as wavelet basis are selected; wavelet transformation is carried out on the collected fingerprint images to obtain low-frequency images, because pixel points of the low-frequency images and the high-frequency images are in one-to-one correspondence, the low-frequency images reserve ridge directions and frequency information of original fingerprint images, and the direction of each pixel obtained through high-frequency estimation can be used as the ridge directions of pixels corresponding to the high-frequency images. Thereby, the invention only considers the information of the low-frequency images to estimate the pixel direction, effectively inhibits the influence of high-frequency noise on fingerprint image quality, realizes the strengthening of the fingerprint images and improves the quality of the fingerprint images, thus improving the fingerprint recognition accuracy and the recognition speed, meeting more practical application requirements of the fingerprint recognition and widening the application range of the fingerprint recognition.

Description

technical field [0001] The invention relates to the technical field of biological identification, in particular to a fingerprint identification preprocessing method and device. Background technique [0002] Biometrics refers to the identification of people based on their physiological or behavioral characteristics. Biometrics relies on the inherent attributes of the human body, there is no problem of forgetting or losing, and the biometrics are unique, so biometrics can theoretically achieve high security. The main biometric technologies include face recognition, fingerprint recognition, hand type recognition, iris recognition, retina recognition, voice recognition, signature recognition and so on. In comparison, fingerprint recognition has the advantages of high accuracy, fast speed, convenient fingerprint collection, sufficient understanding of fingerprint characteristics, legal recognition, easy acceptance by people, and large market share. And application is a hot issu...

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): G06K9/40G06K9/38G06K9/00
Inventor 陈礼攀杨钰杨文奕周封
Owner BEIJING YICHUANG 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