Trusted identity authentication system based on block chain

By dividing the image into sub-images and encrypting storage processing, the problem of low recognition efficiency in blockchain technology in identity authentication is solved, and a fast identity authentication process is realized.

CN119004432APending Publication Date: 2024-11-22LUDONG UNIVERSITY
View PDF 0 Cites 2 Cited by

Patent Information

Application Number
CN202411011108.0
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-07-26
Publication Date
2024-11-22

AI Technical Summary

Technical Problem

When using blockchain technology to authenticate trusted identity, the recognition efficiency is low, especially when processing a large number of authentication requests, all feature information of the entire image needs to be decrypted, resulting in a slower authentication process.

Method used

The image is divided into multiple sub-images with the same area, and the features of each sub-image are encrypted and stored and processed. During identity authentication, the similarity is compared in the order of authentication coefficients from large to small, and the verification results are quickly obtained.

Benefits of technology

It improves the efficiency of trusted identity authentication, reduces the need to obtain feature information of all pixels, and significantly speeds up the authentication process.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119004432A_ABST
    Figure CN119004432A_ABST
Patent Text Reader

Abstract

The invention belongs to the field of identity authentication, and discloses a block chain-based trusted identity authentication system, which comprises an acquisition device, a feature extraction device, a data encryption device, a data storage device, an identity authentication device and a data comparison device, the acquisition device is used for acquiring a first image containing authentication information of a person needing identity authentication; the feature extraction device is used for dividing the first image into a plurality of first sub-images with the same area and respectively acquiring a first image feature of each first sub-image; the data encryption device is used for encrypting the first image feature to obtain an encryption feature, and is used for storing the encryption feature corresponding to each first sub-image by adopting a block chain technology; the identity authentication device is used for acquiring a second image containing authentication information of a person needing identity authentication when credible identity authentication is carried out; the data comparison device is used for carrying out trusted identity authentication based on the second image. According to the invention, the efficiency of trusted identity authentication is improved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of identity authentication, and in particular to a trusted identity authentication system based on blockchain. Background Art

[0002] In order to improve the security of the trusted identity verification process, the existing technology has emerged to use blockchain technology for trusted identity authentication. Compared with ordinary authentication methods, the main difference is that the reserved verification information is stored using blockchain technology. Blockchain technology can help protect the privacy and security of reserved verification information. Because blockchain is decentralized, it is not easy to be hacked and tampered with. Everyone's reserved verification information can be encrypted and stored on the blockchain, and only authorized people can access this data.

[0003] Since the reserved verification information is encrypted, in the existing technology, for example, when performing face recognition based on blockchain technology, the feature information of the entire image is usually encrypted and then stored using blockchain technology. This can easily lead to low recognition efficiency, that is, it may take a long time to get the authentication result, because when a system needs to process a large number of authentication requests at the same time, each request involves the process of decrypting all the feature information of the entire image. Summary of the invention

[0004] The purpose of the present invention is to disclose a trusted identity authentication system based on blockchain, so as to solve the problem of how to improve the authentication efficiency when using blockchain technology for trusted identity authentication.

[0005] In order to achieve the above object, the present invention provides the following technical solutions:

[0006] The present invention provides a trusted identity authentication system based on blockchain, including a collection device, a feature extraction device, a data encryption device, a data storage device, an identity authentication device and a data comparison device;

[0007] The acquisition device is used to obtain a first image containing authentication information of a person who needs to be authenticated;

[0008] The feature extraction device is used to divide the first image obtained by the acquisition device into a plurality of first sub-images of the same area according to a preset segmentation rule, and to respectively obtain the first image feature of each first sub-image using a preset acquisition algorithm;

[0009] The data encryption device is used to encrypt the first image feature to obtain the encrypted feature, and is used to store the encrypted feature corresponding to each first sub-image respectively using blockchain technology;

[0010] The identity authentication device is used to obtain a second image containing authentication information of a person who needs to be authenticated when performing trusted identity authentication;

[0011] The data comparison device is used to perform trusted identity authentication in the following manner:

[0012] S1, using a preset segmentation rule to divide the second image into a plurality of second sub-images of the same area;

[0013] S2, respectively calculating the authentication coefficient of each second sub-image;

[0014] S3, numbering each second sub-image in descending order of the authentication coefficient, starting from 1;

[0015] S4, initialize k to 1;

[0016] S5, using a preset acquisition algorithm to acquire a second image feature of a second sub-image numbered k;

[0017] S6, obtaining from a data storage device an encrypted feature of the first sub-image having the same position as the second sub-image numbered k;

[0018] S7, decrypting the encrypted feature to obtain a first image feature;

[0019] S8, calculating the similarity between the first image feature obtained in S7 and the second image feature obtained in S5, and determining whether the similarity is greater than a set similarity threshold. If so, proceeding to S9; if not, it indicates that the trusted identity authentication fails, and the authentication ends;

[0020] S9, determine whether k is equal to N 2 , N 2 represents the total number of the first sub-images. If so, it means that the trusted identity authentication is successful; if not, the value of k is increased by 1 and the process goes to S5.

[0021] Preferably, the first image containing authentication information of the person who needs to be authenticated includes any one of a face image, an iris image and a fingerprint image.

[0022] Preferably, the preset segmentation rules include:

[0023] L and W are used to represent the length and width of the image to be segmented, respectively; N 2 Indicates the number of sub-images obtained by division;

[0024] Calculate the length of the sub-image subL:

[0025]

[0026] Calculate the width subW of the sub-image:

[0027]

[0028] Divide the image to be segmented into N 2 A sub-image with a length of subL and a width of subW.

[0029] Preferably, the preset acquisition algorithm includes an ORB algorithm.

[0030] Preferably, encrypting the first image feature to obtain the encrypted feature includes:

[0031] An asymmetric encryption algorithm is used to encrypt the first image feature to obtain an encrypted feature.

[0032] Preferably, encrypting the first image feature to obtain the encrypted feature includes:

[0033] The first image feature is encrypted using a symmetric encryption algorithm to obtain an encrypted feature.

[0034] Preferably, obtaining a second image containing authentication information of a person who needs to be authenticated includes:

[0035] The second image is acquired using the same acquisition parameters as the first image.

[0036] Preferably, the type of the first image and the type of the second image are the same.

[0037] Preferably, the calculation formula of the authentication coefficient is as follows:

[0038]

[0039] certcoef c represents the authentication coefficient of the second sub-image c, Nedg c Indicates the total number of edge pixels contained in c, Nall c Indicates the total number of pixels contained in c, distmid c represents the distance between the center of sub-image c and the center of the second image, distmid max represents the maximum distance between the center of all second sub-images and the center of the second image, pxuc represents the set of pixels in c, pixgray i represents the gray value of pixel i, pixgrayave represents the average gray value of pixels in c, α1, α2 and α3 are edge weight, distance weight and information weight respectively.

[0040] Preferably, the similarity threshold is set to 0.8.

[0041] Beneficial effects:

[0042] Compared with the existing technology, the present invention does not directly store the feature information of the entire image during the process of trusted identity authentication, but divides the image as reserved information into multiple sub-images, and then encrypts and stores the feature information of each sub-image respectively. Afterwards, when performing trusted identity authentication, the present invention can compare the similarity of each sub-image corresponding to the image obtained by the identity authentication device. In this way, when the identity of the person who needs to be authenticated does not belong to the person for whom the information for verification is reserved, there is no need to obtain the feature information of all pixels, and the verification result can be quickly obtained, which effectively improves the efficiency of trusted identity authentication. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for describing the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0044] Figure 1 A schematic diagram of a blockchain-based trusted identity authentication system of the present invention. DETAILED DESCRIPTION

[0045] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0046] like Figure 1 As shown, the present invention provides a trusted identity authentication system based on blockchain, including a collection device, a feature extraction device, a data encryption device, a data storage device, an identity authentication device and a data comparison device;

[0047] The acquisition device is used to obtain a first image containing authentication information of a person who needs to be authenticated;

[0048] The feature extraction device is used to divide the first image obtained by the acquisition device into a plurality of first sub-images of the same area according to a preset segmentation rule, and to respectively obtain the first image feature of each first sub-image using a preset acquisition algorithm;

[0049] The first image feature may be in the form of a feature vector;

[0050] The data encryption device is used to encrypt the first image feature to obtain the encrypted feature, and is used to store the encrypted feature corresponding to each first sub-image respectively using blockchain technology;

[0051] The encrypted feature vectors are recorded on the blockchain. Because of the decentralization and immutability of the blockchain, the data stored on it is safe and reliable. Each feature vector is timestamped and has associated access records to ensure transparency and traceability.

[0052] The identity authentication device is used to obtain a second image containing authentication information of a person who needs to be authenticated when performing trusted identity authentication;

[0053] The data comparison device is used to perform trusted identity authentication in the following manner:

[0054] S1, using a preset segmentation rule to divide the second image into a plurality of second sub-images of the same area;

[0055] S2, respectively calculating the authentication coefficient of each second sub-image;

[0056] S3, numbering each second sub-image in descending order of the authentication coefficient, starting from 1;

[0057] S4, initialize k to 1;

[0058] S5, using a preset acquisition algorithm to acquire a second image feature of a second sub-image numbered k;

[0059] S6, obtaining from a data storage device an encrypted feature of the first sub-image having the same position as the second sub-image numbered k;

[0060] S7, decrypting the encrypted feature to obtain a first image feature;

[0061] S8, calculating the similarity between the first image feature obtained in S7 and the second image feature obtained in S5, and determining whether the similarity is greater than a set similarity threshold. If so, proceeding to S9; if not, it indicates that the trusted identity authentication fails, and the authentication ends;

[0062] S9, determine whether k is equal to N 2 , N 2 represents the total number of the first sub-images. If so, it means that the trusted identity authentication is successful; if not, the value of k is increased by 1 and the process goes to S5.

[0063] In the process of trusted identity authentication, the feature information of the entire image is not directly stored. Instead, the image as reserved information is divided into multiple sub-images, and the feature information of each sub-image is encrypted and stored respectively. Afterwards, when performing trusted identity authentication, the present invention can compare the similarity of each sub-image corresponding to the image obtained by the identity authentication device respectively. In this way, when the identity of the person who needs to be authenticated does not belong to the person for whom the information for verification is reserved, there is no need to obtain the feature information of all pixels, and the verification result can be quickly obtained, which effectively improves the efficiency of trusted identity authentication.

[0064] Preferably, the first image containing authentication information of the person who needs to be authenticated includes any one of a face image, an iris image and a fingerprint image.

[0065] Preferably, in the process of obtaining the first image containing the authentication information of the person who needs to be authenticated, if the first image is a face image, the facial outline is displayed on the plane of the terminal device used by the user, and the photo is taken only when the facial outline of the user is completely inside the displayed facial outline to obtain the first image.

[0066] Preferably, the preset segmentation rules include:

[0067] L and W are used to represent the length and width of the image to be segmented, respectively; N 2 Indicates the number of sub-images obtained by division;

[0068] Calculate the length of the sub-image subL:

[0069]

[0070] Calculate the width subW of the sub-image:

[0071]

[0072] Divide the image to be segmented into N 2 A sub-image with a length of subL and a width of subW.

[0073] Preferably, the preset acquisition algorithm includes an ORB algorithm.

[0074] The ORB algorithm was proposed by Ethan Rublee et al. in 2011 and is mainly used for feature point detection and description in images. ORB combines the FAST feature point detector and the BRIEF feature descriptor and improves them, significantly improving their processing speed and robustness.

[0075] Preferably, encrypting the first image feature to obtain the encrypted feature includes:

[0076] An asymmetric encryption algorithm is used to encrypt the first image feature to obtain an encrypted feature.

[0077] The asymmetric encryption algorithm can be RSA algorithm, DSA algorithm, etc.

[0078] Preferably, encrypting the first image feature to obtain the encrypted feature includes:

[0079] The first image feature is encrypted using a symmetric encryption algorithm to obtain an encrypted feature.

[0080] The symmetric encryption algorithm can be an AES algorithm, a DES algorithm, etc.

[0081] Preferably, obtaining a second image containing authentication information of a person who needs to be authenticated includes:

[0082] The second image is acquired using the same acquisition parameters as the first image.

[0083] Specifically, the acquired parameters include the position of the foreground object in the image and the shooting distance. The foreground object here can be a face, an iris, a fingerprint, etc.

[0084] By controlling the shooting parameters to be the same, it is helpful to quickly locate the target area during the subsequent feature extraction process.

[0085] Preferably, the type of the first image and the type of the second image are the same.

[0086] Specifically, if the first image is a face image, the second image is also a face image. If the first image is an iris image, the second image is also an iris image. If the first image is a fingerprint image, the second image is also a fingerprint image.

[0087] Preferably, the calculation formula of the authentication coefficient is as follows:

[0088]

[0089] certcoef c represents the authentication coefficient of the second sub-image c, Nedg c Indicates the total number of edge pixels contained in c, Nall c Indicates the total number of pixels contained in c, distmid c represents the distance between the center of sub-image c and the center of the second image, distmid max represents the maximum distance between the center of all second sub-images and the center of the second image, pxuc represents the set of pixels in c, pixgray irepresents the gray value of pixel i, pixgrayave represents the average gray value of pixels in c, α1, α2 and α3 are edge weight, distance weight and information weight respectively.

[0090] The authentication coefficient of the present invention is calculated comprehensively from three types of data, so that the authentication coefficient can more comprehensively and effectively represent the number of valid image features contained in the sub-image. Specifically, if the number of pixel points belonging to the edge is greater, the distance from the center of the image is closer, and the difference between the grayscale values ​​of different pixel points is greater, then the authentication coefficient is greater, indicating that the sub-image contains more valid image features; and if the number of pixel points belonging to the edge is less, the distance from the center of the image is farther, and the difference between the grayscale values ​​of different pixel points is smaller, then the authentication coefficient is smaller, indicating that the sub-image contains fewer valid image features.

[0091] Therefore, in the subsequent comparison process, the present invention numbers the second sub-image in descending order according to the authentication coefficient. The larger the authentication coefficient, the smaller the number and the earlier the comparison is performed. The authentication result can be obtained after obtaining image features of fewer pixels, thereby improving the efficiency of authentication.

[0092] Preferably, the edge weight, distance weight and information weight are 0.3, 0.3 and 0.4 respectively.

[0093] Preferably, the similarity threshold is set to 0.8.

[0094] Preferably, the process of acquiring the first image feature of the first sub-image by using a preset acquisition algorithm includes:

[0095] Performing image segmentation processing on the first image to obtain a foreground area in the first image; this step only requires one calculation and can be applied to the process of obtaining first image features for each first sub-image;

[0096] Performing grayscale processing and noise reduction processing on the first sub-image in sequence to obtain a pre-processed image;

[0097] The above processing can improve the accuracy of recognition.

[0098] Obtain a local area belonging to the foreground area in the preprocessed image;

[0099] The image feature of the local area is acquired using a preset acquisition algorithm to obtain the first image feature.

[0100] Specifically, the process of acquiring the second image feature of the second sub-image is the same as the process of acquiring the first image feature of the first sub-image.

[0101] It is obvious to those skilled in the art that the present invention is not limited to the details of the above-mentioned exemplary embodiments, and that the present invention can be implemented in other specific forms without departing from the spirit or essential features of the present invention; therefore, no matter from which point of view, the embodiments should be regarded as exemplary and non-restrictive, and the scope of the present invention is limited by the appended claims rather than the above description, and therefore it is intended to include all changes within the meaning and scope of the equivalent elements of the claims within the present invention, and any figure mark in the claims should not be regarded as limiting the claims involved.

[0102] In addition, it should be understood that although the present specification is described according to implementation modes, not every implementation mode contains only one independent technical solution. This description of the specification is only for the sake of clarity. Those skilled in the art should regard the specification as a whole. The technical solutions in each embodiment may also be appropriately combined to form other implementation modes that can be understood by those skilled in the art.

Claims

1. A trusted identity authentication system based on blockchain, characterized in that: It includes a collection device, a feature extraction device, a data encryption device, a data storage device, an identity authentication device and a data comparison device; The acquisition device is used to obtain a first image containing authentication information of a person who needs to be authenticated; The feature extraction device is used to divide the first image obtained by the acquisition device into a plurality of first sub-images of the same area according to a preset segmentation rule, and to respectively obtain the first image feature of each first sub-image using a preset acquisition algorithm; The data encryption device is used to encrypt the first image feature to obtain the encrypted feature, and is used to store the encrypted feature corresponding to each first sub-image respectively using blockchain technology; The identity authentication device is used to obtain a second image containing authentication information of a person who needs to be authenticated when performing trusted identity authentication; The data comparison device is used to perform trusted identity authentication in the following manner: S1, using a preset segmentation rule to divide the second image into a plurality of second sub-images of the same area; S2, respectively calculating the authentication coefficient of each second sub-image; S3, numbering each second sub-image in descending order of the authentication coefficient, starting from 1; S4, initialize k to 1; S5, using a preset acquisition algorithm to acquire a second image feature of a second sub-image numbered k; S6, obtaining from a data storage device an encrypted feature of the first sub-image having the same position as the second sub-image numbered k; S7, decrypting the encrypted feature to obtain a first image feature; S8, calculating the similarity between the first image feature obtained in S7 and the second image feature obtained in S5, and determining whether the similarity is greater than a set similarity threshold. If so, proceeding to S9; if not, it indicates that the trusted identity authentication fails, and the authentication ends; S9, determine whether k is equal to N 2 , N 2 represents the total number of the first sub-images. If so, it means that the trusted identity authentication is successful; if not, the value of k is increased by 1 and the process goes to S5.

2. A blockchain-based trusted identity authentication system according to claim 1, characterized in that: The first image containing authentication information of a person who needs to be authenticated includes any one of a face image, an iris image, and a fingerprint image.

3. A blockchain-based trusted identity authentication system according to claim 1, characterized in that: The preset segmentation rules include: L and W are used to represent the length and width of the image to be segmented, respectively; N 2 Indicates the number of sub-images obtained by division; Calculate the length of the sub-image subL: Calculate the width subW of the sub-image: Divide the image to be segmented into N 2 A sub-image with a length of subL and a width of subW.

4. A blockchain-based trusted identity authentication system according to claim 1, characterized in that: The preset acquisition algorithms include the ORB algorithm.

5. The blockchain-based trusted identity authentication system according to claim 1, characterized in that: The first image feature is encrypted to obtain an encrypted feature, including: The first image feature is encrypted using an asymmetric encryption algorithm to obtain an encrypted feature.

6. A blockchain-based trusted identity authentication system according to claim 1, characterized in that: The first image feature is encrypted to obtain an encrypted feature, including: The first image feature is encrypted using a symmetric encryption algorithm to obtain an encrypted feature.

7. The blockchain-based trusted identity authentication system according to claim 1, characterized in that: Acquiring a second image containing authentication information of a person who needs to be authenticated, including: The second image is acquired using the same acquisition parameters as the first image.

8. The blockchain-based trusted identity authentication system according to claim 1, characterized in that: The type of the first image and the type of the second image are the same.

9. The blockchain-based trusted identity authentication system according to claim 1, characterized in that: The calculation formula of the certification coefficient is as follows: certcoef c represents the authentication coefficient of the second sub-image c, Nedg c Indicates the total number of edge pixels contained in c, Nall c Indicates the total number of pixels contained in c, distmid c represents the distance between the center of sub-image c and the center of the second image, distmid max represents the maximum distance between the center of all second sub-images and the center of the second image, pxuc represents the set of pixels in c, pixgray i represents the gray value of pixel i, pixgrayave represents the average gray value of pixels in c, α1, α2 and α3 are edge weight, distance weight and information weight respectively.

10. A blockchain-based trusted identity authentication system according to claim 1, characterized in that: The similarity threshold is set to 0.8.

Citation Information

Cited By

  • Biological feature recognition method and system

    CN119992671A

  • A biometric recognition method and system

    CN119992671B