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

Finger vein identification method and system based on convolutional neural network

A convolutional neural network and finger vein technology, applied in the field of biometric identification, can solve problems such as inability to effectively extract finger vein pattern information, unclear finger vein patterns, and limited recognition performance of authentication systems

Active Publication Date: 2017-03-22
重庆金融科技研究院 +1
View PDF7 Cites 50 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] In order to solve the problem that the finger vein pattern in the existing finger vein recognition technology is not clear, the finger vein pattern information cannot be effectively extracted, and the recognition performance of the authentication system is limited, etc., the present invention provides a finger vein that can accurately extract the image Finger vein recognition method and system based on convolutional neural network, which can reduce the extraction of wrong features and miss real features, and improve the recognition accuracy of the entire system by using texture information

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
  • Finger vein identification method and system based on convolutional neural network
  • Finger vein identification method and system based on convolutional neural network
  • Finger vein identification method and system based on convolutional neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0064] like figure 1 As shown, Embodiment 1 of the present invention provides a method for recognizing finger veins based on a convolutional neural network. When the present invention is used, the finger area in the image is first extracted and the center matrix is ​​used to correct the rotation and translation of the finger area, and then Mark the vein pixels and background pixels in the finger vein image, and divide the image into sub-blocks with different layers according to these marked pixels, and use these sub-blocks to train the deep convolutional neural network to obtain its high-level feature expression , realize the extraction of the vein pattern features in the finger vein image, and finally authenticate the personal identity by calculating the similarity of the two feature images.

[0065] The specific method includes the following steps:

[0066] S1. Collect the original registered finger vein image, and save the finger vein image in the system.

[0067] S2. Pro...

Embodiment 2

[0080] In the technical solution, in order to improve the accuracy of vein feature segmentation, the finger vein image can be accurately recognized effectively.

[0081] Further, in step S3-3, the probabilistic support vector machine calculates the probability value P that several depth feature vectors in the set of depth feature vectors belong to finger vein features by the following formula,

[0082]

[0083] Among them, ξ(v) represents the output value of the probabilistic support vector machine, and ω and γ represent the two parameters obtained from the training of the probabilistic support vector machine.

Embodiment 3

[0085] In this technical solution, on the basis of Embodiment 1 and Embodiment 2, how to carry out the matching authentication of the pre-identified image is further defined. In step S4-2, the matching score N of the two finger vein feature images is calculated by the following formula (T,R),

[0086]

[0087] in,

[0088]

[0089] If the matching score N(T,R) is less than the preset threshold, the authentication fails; otherwise, the authentication succeeds;

[0090] Wherein, R is the finger vein characteristic image obtained by processing the originally registered finger vein image, T is the finger vein characteristic image obtained by processing the finger vein image to be identified, is a template image, m is the width of the finger vein characteristic image obtained by processing the originally registered finger vein image, n is the height of the finger vein characteristic image obtained by processing the originally registered finger vein image, w is the moving...

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 a finger vein identification method and system based on a convolutional neural network. The method comprises that a finger vein image which is registered originally is collected; the originally registered finger vein image is processed, and a finger vein ROI (Region of Interest) image is extracted from the finger vein image; a finger vein depth feature in a finger vein ROI is extracted via the convolutional neural network, and input to a support vector machine for classification, and further a finger vein enhanced image is obtained; binarization is carried out on the enhanced image to obtain a finger vein feature image; and a model is used to extract features of the pre-identified finger vein image, and the features are matched to realize identity authentication. According to the invention, the finger vein features can be extracted effectively, and the identification precision of the finger vein identification system is improved obviously.

Description

technical field [0001] The invention belongs to the technical field of biological feature recognition, in particular to a method and system for recognizing finger veins based on a convolutional neural network. Background technique [0002] Biometric identification technology uses human biological characteristics or behavioral characteristics for human identity authentication. Among them, behavioral characteristics include signature, voice, gait, etc. Human biological characteristics mainly include two categories: external biological characteristics, such as fingerprints, palms, and irises Vision, face shape, etc.; internal biometrics, such as finger veins, dorsal veins, and palm veins, etc. In external biometrics, fingerprint recognition is widely used due to its uniqueness, stability, and ease of use. However, in fingerprint identification, users must be required to keep their fingers clean and smooth when entering fingerprints, because any dirt or stains on the fingerprint...

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): G06K9/00G06N3/08
CPCG06N3/08G06V40/1347G06V40/1365
Inventor 秦华锋席锋何希平
Owner 重庆金融科技研究院
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

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com