Iris template privacy protection method, system and device based on self-parameterization replacement
The iris data is processed through self-parameterized replacement technology, which solves the problems of privacy leakage and insufficient security in traditional iris recognition technology, and realizes high-precision recognition and high-security iris template privacy protection, meeting the irreversibility of international standards and Revocable requirement.
Patent Information
- Application Number
- CN202210097605.1
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2022-01-27
- Publication Date
- 2024-11-08
- Estimated Expiration
- 2042-01-27
AI Technical Summary
Traditional iris recognition technology has the risk of privacy leakage, and existing iris template privacy protection methods are difficult to meet the requirements of high-precision identification and high security at the same time, especially in terms of noise cancellation and irreversibility, reversibility, and non-connectivity.
Using a method based on self-parameterized permutation, the binary iris data is randomly replaced, segmented and sorted by preset application strings, and the permutation parameters are generated for data permutation, and finally an irreversible, revocable and unconnected iris template is formed.
It achieves irreversibility, revocability and non-connectivity that meets the ISO/IEC 24745 standard, while maintaining good identification performance, ensuring high security and privacy protection of iris data.
Smart Images

Figure CN114463864B_ABST
Abstract
Description
Technical Field
[0001] The present invention belongs to the technical field of biometric data privacy protection, and relates to a privacy protection method, system and electronic device for iris data during iris recognition, and specifically to a privacy protection method, system and electronic device for iris templates based on self-parameterization replacement. Background Art
[0002] With the continuous development of information technology, people are increasingly relying on the convenience brought by biometric technology. However, with the widespread application of biometric technology (such as fingerprints, irises, faces, etc.), our biometric data is also widely used in various application scenarios we have used. Generally speaking, most of a person's biometric information will not change throughout his life. Traditional biometric identification schemes use plain text to identify directly, which poses a serious risk of privacy leakage. If personal biometric data is stored in the database in plain text, once the data is stolen by an attacker, it will have an irreversible impact on the individual or society. Therefore, many people have proposed that biometric data must be protected to prevent personal biometric information from being leaked. According to ISO / IEC 24745, the privacy protection of biometric templates must meet the following requirements: irreversibility, revocability, and non-connectability (that is, cross-matching). Iris recognition technology is one of the most important biometric technologies. Compared with other biometrics, irises are more stable and unique.
[0003] At present, there are many iris template privacy protection methods, which can be roughly divided into two categories, namely biometric encryption system and revocable biometrics. Biometric encryption system mainly achieves the purpose of privacy protection by combining with cryptography. Since some noise is often generated when collecting biometric data, the difficulty of this type of method is often how to eliminate the noise of biometric data. Biometric encryption system can be divided into two parts: biometric encryption method based on key generation and biometric encryption method with key binding. Among them, for the biometric encryption method with key generation, its key is based on the data generated by the biometric data itself, that is, the key is generated based on the biometric data itself. For the biometric encryption method with key binding, its key is directly bound to the biometric data, that is, the key exists independently. Revocable biometric technology refers to converting iris data from one domain to another by performing some irreversible transformation or salting operations on the biometric data, and still supports recognition after the transformation. Therefore, it is very meaningful to propose an iris template privacy protection method with both high-precision recognition effect and high security. Summary of the invention
[0004] In order to overcome the defects of the above-mentioned background technology, the present invention provides an iris template privacy protection method and system based on self-parameterization replacement.
[0005] The technical solution adopted by the method of the present invention is: an iris template privacy protection method based on self-parameterization replacement, comprising the following steps:
[0006] Step 1: Use the preset application string to randomly permute the binary iris data x;
[0007] Step 2: Divide the iris data processed in step 1 into two parts, X and P;
[0008] Step 3: Divide P into blocks and calculate the decimal value of each block;
[0009] Step 4: Group the decimal value v obtained in step 3 to obtain p;
[0010] Step 5: Sort the decimal values of each group and record the sorted values within the group;
[0011] Step 6: Group X, and the length of the group is consistent with P;
[0012] Step 7: Use the decimal value of each group in P as a replacement parameter to replace each group of iris data in X;
[0013] Step 8: Save the X replaced in step 7 as the iris template.
[0014] The technical solution adopted by the system of the present invention is: an iris template privacy protection system based on self-parameterization replacement, including the following modules:
[0015] Module 1, used to randomly permute binary iris data x using a preset application string;
[0016] Module 2 is used to divide the iris data processed by module 1 into two parts, X and P;
[0017] Module 3, used to divide P into blocks and calculate the decimal value of each block;
[0018] Module 4 is used to perform grouping processing on the decimal value v obtained in module 3 to obtain p;
[0019] Module 5, used for sorting the decimal values of each group and recording the sorted values within the group;
[0020] Module 6 is used to group X, and the length of the group is consistent with P;
[0021] Module 7, used for replacing each group of iris data in X by using the decimal value of each group in P as a replacement parameter;
[0022] Module 8 is used to save the X replaced in module 7 as an iris template.
[0023] The technical solution adopted by the device of the present invention is: an electronic device, comprising: one or more processors; a storage device for storing one or more programs, when the one or more programs are executed by the one or more processors, the one or more processors implement an iris template privacy protection method based on self-parameterization replacement.
[0024] The beneficial effects of the present invention are: the irreversibility, revocability and non-connectability proposed by the international standard ISO / IEC 24745 for iris template protection are met at the same time, and the method can obtain good recognition performance. BRIEF DESCRIPTION OF THE DRAWINGS
[0025] Figure 1 Schematic diagram of the method according to an embodiment of the present invention. DETAILED DESCRIPTION
[0026] In order to facilitate ordinary technicians in the field to understand and implement the present invention, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the implementation examples described herein are only used to illustrate and explain the present invention, and are not used to limit the present invention.
[0027] Please see Figure 1 The present invention provides an iris template privacy protection method based on self-parameterization replacement, comprising the following steps:
[0028] Step 1: The iris data is first replaced with the preset application string.
[0029] for Figure 1 The l-bit iris data x and the l-bit preset application string I are replaced to convert x into s;
[0030] Step 2: Divide s into two parts, X and P, where the length of X is m and the length of P is 1m;
[0031] Step 3: Divide P into m blocks, each of which has a length of k. The decimal value of each block is:
[0032]
[0033] Step 4: Group the decimal value v obtained in step 3 to obtain p; wherein v is divided into n groups, and p = p0…p n-1 ;
[0034] Step 5: Sort the decimal values in p within the group and record their sort values. If v i and v j If the values are the same, compare the subscripts i and j.
[0035] Step 6: Divide X into n groups and obtain X = X0…X n-1 .
[0036] Step 7: According to p i The sorted value pairs X in (i=0...n-1) i Perform bitwise permutations.
[0037] Step 8: Save the permuted X as template t, and delete x, X, P, v, and p.
[0038] The final template t in the image is stored instead of the initial iris data x.
[0039] The present invention can meet the privacy requirements of iris template protection and support effective iris recognition.
[0040] It should be understood that the above description of the preferred embodiment is relatively detailed and cannot be regarded as limiting the scope of patent protection of the present invention. For ordinary technicians in this field, they can make substitutions or modifications based on the above description, and all these substitutions or modifications should fall within the scope of protection of the claims attached to the present invention.
Claims
1. A privacy protection method for iris template based on self-parameterization replacement, It is characterized in that The following steps are involved: Step 1: Use the preset application string to analyze the binary iris data x Perform random permutations; Among them, for any l Iris data x and l Preset application string I , perform a permutation operation, x Convert to s ; Step 2: Divide the iris data processed in step 1 into X and P Two parts; Step 3: Right P Divide into blocks and calculate the decimal value of each block; in, X The length is m , P The length is l-m ;Will P Divide m blocks, each block is of length k , then the decimal value of each block is: ; Step 4: For the decimal value obtained in step 3 v Perform group processing and obtain p ; Step 5: Sort the decimal values of each group and record the sorted values within the group; Among them, if two groups v i and v j The values are equal, according to the subscript i and j Sort by size; Step 6: Right X For group processing, the length of the group is P Stay consistent; Step 7: P The decimal value of each group is used as a replacement parameter pair. X Replace the iris data of each group; Step 8: Replace the X Save as an iris template; Among them, save the replaced X as template t and delete x,X,P,v and p .
2. An iris template privacy protection system based on self-parameterization replacement, used to implement the method described in claim 1; It is characterized in that Includes the following modules: Module 1 is used to use a preset application string to process binary iris data x Perform random permutations; Module 2 is used to divide the iris data processed by module 1 into X and P Two parts; Module 3, for P Divide into blocks and calculate the decimal value of each block; Module 4, for the decimal value obtained for module 3 v Perform group processing and obtain p ; Module 5, used for sorting the decimal values of each group and recording the sorted values within the group; Module 6, for X For group processing, the length of the group is P Stay consistent; Module 7, used to P The decimal value of each group is used as a replacement parameter pair. X Replace the iris data of each group; Module 8 is used to replace the X Save as an iris template.
3. A device, It is characterized in that include: one or more processors; A storage device is used to store one or more programs. When the one or more programs are executed by the one or more processors, the one or more processors implement the iris template privacy protection method based on self-parameterization replacement as claimed in claim 1.
Citation Information
Patent Citations
Iris template protection method based on local sorting
CN107944290A
Iris template protection method and system combining local sorting and negative database
CN111274571A
Unified real-time microprocessor computer
US20020091991A1
