A Heterogeneous Iris Authentication Method with Stealing Attack Mechanism

An authentication method, iris technology, applied in digital data authentication, computer parts, instruments, etc.

Active Publication Date: 2019-11-01
JILIN UNIV
View PDF11 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0009] The main purpose of the present invention is to solve some problems existing in the existing iris authentication method;

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
  • A Heterogeneous Iris Authentication Method with Stealing Attack Mechanism
  • A Heterogeneous Iris Authentication Method with Stealing Attack Mechanism
  • A Heterogeneous Iris Authentication Method with Stealing Attack Mechanism

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0067] Under the framework of claim 1, the operation of a certain person (named A, A’s information is stored in the authentication system, and the test iris and the template iris are the same equipment, the same collection environment is used for collection, and no theft attack occurs) The whole process:

[0068] 1) The computer first collects the iris image of A through the iris collector, and then converts the eye image of A into a 256×32-dimensional iris normalized and enhanced image through the Daugman rubber band method and equalized histogram, and normalizes the iris of A to An augmented image is input into a convolutional layer.

[0069] 2) The iris normalized enhanced image of A goes through the first convolutional layer, the first pooling layer, the first ReLU layer, the second convolutional layer, the second pooling layer, the second ReLU layer, and the third convolutional layer , the third pooling layer, the image processing layer, and the tiling layer, enter the f...

Embodiment 2

[0074] Under the framework of claim 1, for a certain person (named B, the information of B is not saved in the authentication system, it belongs to a new category, and the test iris and the template iris will be collected through different equipment and different collection environments, and there is no theft attack behavior Occurrence) The whole process of operation:

[0075] 1) The computer first collects H iris images of B through the iris collector p, and then converts the H images of B's ​​eyes into 256×32-dimensional iris normalized enhanced images through the Daugman rubber band method and equalized histogram. The iris normalized and enhanced images of H sheets of B are sequentially input into the convolutional layer.

[0076] 2) The iris normalized enhanced images of H pieces of B go through the first convolutional layer, the first pooling layer, the first ReLU layer, the second convolutional layer, the second pooling layer, the second ReLU layer, and the third volume ...

Embodiment 3

[0085] Under the framework of claim 1, the whole operation process of a certain person (named C, C’s information is not saved in the authentication system, and no theft attack occurs):

[0086] 1) The computer first collects the iris image of C through the iris collector, and then converts the eye image of C into a 256×32-dimensional iris normalized and enhanced image through the Daugman rubber band method and equalized histogram, and normalizes the iris of A to An augmented image is input into a convolutional layer.

[0087] 2) The iris normalized enhanced image of C passes through the first convolutional layer, the first pooling layer, the first ReLU layer, the second convolutional layer, the second pooling layer, the second ReLU layer, and the third convolutional layer , the third pooling layer, the image processing layer, and the tiling layer, enter the fully connected layer.

[0088] 3) From the tiling layer to the fully connected layer, the 15 data of the tiling layer a...

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 heterogeneous iris authentication method with a stealing attack coping mechanism. The method is as follows: step 1, constructing a heterogeneous iris multi-category authentication system improved based on a convolutional neural network; step 2, constructing a stealing attack Coping mechanism; step 3, start formal authentication; step 4, the image enters the fully connected layer in turn; step 5, obtain the similarity probability with the iris belonging to a single classifier; step 6, obtain the accurate similarity probability; step 7, pass the coding layer The mapping relationship, output the iris category to which the test iris belongs. Beneficial effects: The traditional convolutional neural network is transformed, and the image processing layer and the dilution layer are added, which helps to enlarge the difference between different types of irises in multi-category authentication and improves the accuracy of authentication.

Description

[0001] The invention relates to a heterogeneous iris authentication method, in particular to a heterogeneous iris authentication method with a stealing attack response mechanism. Background technique [0002] At present, with the development of social informatization, biometric technologies such as face, iris, and fingerprints have begun to be used on a large scale in actual production and life. The iris, as a human body feature that is not easy to be copied, is favored by those places with high confidentiality and high security, such as military bases and vaults. [0003] The current iris authentication mainly adopts the coded recognition mode, that is, after preprocessing the qualified iris, the test iris and the contrast iris as a template are converted into feature codes in the same way, and through a certain The algorithm compares the similarity between the features, and then completes the iris authentication. This mode is currently the most widely studied and most commo...

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 Patents(China)
IPC IPC(8): G06K9/00G06N3/04G06F21/32
CPCG06F21/32G06V40/197G06N3/045
Inventor 刘元宁刘帅朱晓冬董立岩程垚松崔靖威张齐贤丁通张阔肖刚毅
Owner JILIN UNIV
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