Riesz wavelet and SSLM (Small Sphere and Large Margin) model-based vein recognition method

A technology of vein recognition and model, applied in the field of image recognition

Inactive Publication Date: 2017-02-15
CIVIL AVIATION UNIV OF CHINA
View PDF8 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

First, finger vein detection requires a living body. Finger vein images can only be obtained when detecting a living body, which is very safe; second, finger veins are a feature of the body, and external factors will not cause obstacles to recognition. Good anti-interference; Third, everyone's finger vein images are different, unique and irreplaceable

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
  • Riesz wavelet and SSLM (Small Sphere and Large Margin) model-based vein recognition method
  • Riesz wavelet and SSLM (Small Sphere and Large Margin) model-based vein recognition method
  • Riesz wavelet and SSLM (Small Sphere and Large Margin) model-based vein recognition method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0074] The vein identification method based on Riesz wavelet and SSLM model provided by the present invention will be described in detail below with reference to the accompanying drawings and specific embodiments.

[0075] The vein identification method based on Riesz wavelet and SSLM model provided by the present invention comprises the following steps in order:

[0076] 1) Normalize each original finger vein image collected to 2 m ×2 m Rectangular image of size;

[0077] 2) Perform N-order Riesz transformation on each of the above-mentioned normalized finger vein images to obtain N+1 Riesz transformed images. The transformation formula used in Riesz transformation is shown in formula (1):

[0078]

[0079] where R N Represents the N-order Riesz transform, which is composed of N+1 single-kernel R (n，N-n) Composition; the calculation formula of Riesz single core is shown in formula (2):

[0080]

[0081]

[0082] where w is the frequency, from the horizontal freq...

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 relates to a Riesz wavelet and SSLM (Small Sphere and Large Margin) model-based vein recognition method. According to the method, feature extraction is based on Riesz wavelets; Riesz transformation is the multidimensional expansion of Hilbert transformation, has good spectral directivity, and can avoid amplitude change before and after transformation. Based on the combination of the Riesz transformation and wavelets, the Riesz wavelets not only maintain original directivity, but also additionally have scale invariant performance. When the Riesz wavelets are adopted to process vein images, texture features of the vein images in different directions and different scales can be effectively extracted. An SSLM model is adopted, positive sample points can be surrounded by using a hypersphere which can be as small as possible, and negative sample points are separated through using larger intervals, and therefore, few negative samples can be used to complete model construction. The center of the hypersphere can greatly represent the positive samples, and therefore, texture signatures of multiple scales can be generated. The method has the advantages of high speed, good effect, great physical significance and the like.

Description

technical field [0001] The invention belongs to the technical field of image recognition, in particular to a vein recognition method based on Riesz wavelet and SSLM model. Background technique [0002] Modern biometric identification technology is developing in an accurate, safe and fast direction, while traditional biometric identification, such as fingerprints and voice, has long been unable to meet people's security needs. As a new type of biometric identification technology, finger vein has many advantages over traditional methods. First, finger vein detection has living requirements. Only when detecting living bodies can get finger vein images, which has good security. Second, finger veins are characteristics of the body, and external factors will not cause obstacles in identification. Good anti-interference; third, each person's finger vein images are different, unique and irreplaceable. SUMMARY OF THE INVENTION [0003] In order to solve the above problems, the pu...

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): G06K9/00G06K9/46G06K9/62
CPCG06V40/10G06V40/14G06V10/449G06F18/214
Inventor 杨金锋卫建泽师一华
Owner CIVIL AVIATION UNIV OF CHINA
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