Iris-based identity recognition method and apparatus

Abstract

The embodiment of the present application discloses an iris-based identity recognition method and device, which can be used in the financial field or other technical fields, and the method comprises the following steps: inputting the iris image of a customer into a preset feature extraction model to obtain iris features extracted by the feature extraction model; acquiring an encryption function corresponding to each iris template in an iris template library, wherein the iris template contains iris features, the iris features in the iris template contain real features and false features, the encryption function is established according to all real features in the corresponding iris template, and the encryption function can be decrypted by any real feature in the corresponding iris template; and the iris template matched with the customer is determined by decrypting each encryption function by using the iris features extracted by the feature extraction model, so as to determine the identity information of the customer. The present application helps to improve the security of the iris information of the customer.

Description

Technical Field

[0001] This invention relates to the field of iris recognition technology, and more specifically, to an iris-based identity recognition method and apparatus. Background Technology

[0002] Currently, iris recognition involves capturing a user's iris image, extracting iris features based on a model, and matching these features against iris templates in a database to determine the user's identity. Iris templates are real information reserved for customer identification, containing the customer's identity information and iris features. However, the iris template database currently lacks security protection. If a template is stolen, the user's important information can be exploited by criminals, posing a significant security risk. Protecting customers' iris information from misuse is a pressing technical problem that needs to be addressed. Summary of the Invention

[0003] In order to solve at least one of the technical problems in the background art, the present invention proposes an iris-based identity recognition method and device.

[0004] To achieve the above objectives, according to one aspect of the present invention, an iris-based identity recognition method is provided, the method comprising:

[0005] Obtain the customer's iris image;

[0006] The iris image is input into a preset feature extraction model to obtain the iris features extracted by the feature extraction model. The iris features extracted by the feature extraction model include real features and false features. The feature extraction model includes a first neural network and a second neural network. The first neural network extracts real features from the iris image, and the second neural network extracts false features from the iris image.

[0007] Obtain the encryption function corresponding to each iris template in the iris template library. The iris template contains iris features, which include real features and fake features. The encryption function is established based on all real features in the corresponding iris template and can be decrypted by any real feature in the corresponding iris template.

[0008] By using the iris features extracted by the feature extraction model to attempt to decrypt each encryption function, an iris template matching the customer is determined, thereby identifying the customer's identity information.

[0009] Optionally, by using the iris features extracted by the feature extraction model to attempt to decrypt each encryption function, an iris template matching the customer can be determined, thereby determining the customer's identity information, specifically including:

[0010] By using the iris features extracted by the feature extraction model to attempt to decrypt each encryption function, the target encryption function is determined. The target encryption function is the encryption function with the most decryptable features among the iris features extracted by the feature extraction model.

[0011] The iris template corresponding to the target encryption function is determined as the iris template that matches the customer, and then the customer's identity information is determined based on the iris template that matches the customer.

[0012] Optionally, by using the iris features extracted by the feature extraction model to attempt to decrypt each encryption function, an iris template matching the customer can be determined, thereby determining the customer's identity information, specifically including:

[0013] By using the iris features extracted by the feature extraction model to attempt to decrypt each encryption function, the true features in the iris features extracted by the feature extraction model are determined. The true features are the iris features extracted by the feature extraction model that can decrypt the encryption function.

[0014] Calculate the similarity between the determined true features and the iris features of each iris template;

[0015] If the maximum similarity value is greater than a preset threshold, the iris template corresponding to the maximum similarity value is determined as the iris template that matches the customer, and then the customer's identity information is determined based on the iris template that matches the customer.

[0016] Optionally, the iris-based identity recognition method further includes:

[0017] Obtain training samples, wherein the training samples include: iris images used for model training and fake iris images generated based on the iris images used for model training;

[0018] The feature extraction model is trained based on the training samples. During training, the iris image used for model training is input into the first neural network to train the first neural network, and the fake iris image is input into the second neural network to train the second neural network.

[0019] An iris template is established based on the real features extracted from the iris image used for model training by the first neural network and the fake features extracted from the fake iris image by the second neural network.

[0020] Optionally, the iris-based identity recognition method further includes:

[0021] An encryption function is established based on the real features extracted from the iris image used for model training by the first neural network, and a correspondence is set between the established encryption function and the established iris template.

[0022] Optionally, the fake iris image is specifically obtained by stitching together the iris image used for model training with at least one other iris image.

[0023] Optionally, when training the feature extraction model, the first neural network is trained using a first loss function, and the second neural network is trained using a second loss function, wherein the second loss function is the reciprocal of the first loss function.

[0024] To achieve the above objectives, according to another aspect of the present invention, an iris-based identity recognition device is provided, the device comprising:

[0025] Iris image acquisition unit, used to acquire the customer's iris image;

[0026] An iris feature extraction unit is used to input the iris image into a preset feature extraction model to obtain iris features extracted by the feature extraction model. The iris features extracted by the feature extraction model include real features and false features. The feature extraction model includes a first neural network and a second neural network. The first neural network extracts real features from the iris image, and the second neural network extracts false features from the iris image.

[0027] The encryption function acquisition unit is used to acquire the encryption function corresponding to each iris template in the iris template library. The iris template contains iris features, which include real features and fake features. The encryption function is established based on all real features in the corresponding iris template, and the encryption function can be decrypted by any real feature in the corresponding iris template.

[0028] The identity recognition unit is used to decrypt each encryption function by using the iris features extracted by the feature extraction model to determine the iris template that matches the customer, thereby determining the customer's identity information.

[0029] To achieve the above objectives, according to another aspect of the present invention, a computer device is also provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the above-described iris-based identity recognition method.

[0030] To achieve the above objectives, according to another aspect of the present invention, a computer-readable storage medium is also provided, on which a computer program / instructions are stored, which, when executed by a processor, implement the steps of the above-described iris-based identity recognition method.

[0031] To achieve the above objectives, according to another aspect of the present invention, a computer program product is also provided, comprising a computer program / instructions that, when executed by a processor, implement the steps of the iris-based identity recognition method described above.

[0032] The beneficial effects of this invention are as follows:

[0033] This invention improves the iris template by incorporating fake features into the iris characteristics. This results in a mixture of real and fake features in the iris template. Consequently, even if the iris template is stolen, criminals will only obtain iris characteristics mixed with fake features. Since criminals cannot distinguish between real and fake features, they cannot obtain the customer's true iris characteristics even if they steal the iris template. Therefore, this invention effectively protects the iris template and improves the security of the customer's iris information. Attached Figure Description

[0034] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort. In the drawings:

[0035] Figure 1 This is a flowchart of the iris-based identity recognition method according to an embodiment of the present invention;

[0036] Figure 2 This is a first flowchart of an embodiment of the present invention for determining identity information;

[0037] Figure 3 This is a second flowchart illustrating the process of determining identity information according to an embodiment of the present invention;

[0038] Figure 4 This is a schematic diagram of the model training process according to an embodiment of the present invention;

[0039] Figure 5 This is a structural block diagram of an iris-based identity recognition device according to an embodiment of the present invention;

[0040] Figure 6 This is a schematic diagram of a computer device according to an embodiment of the present invention. Detailed Implementation

[0041] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0042] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0043] It should be noted that the terms "comprising" and "having" and any variations thereof in the specification, claims and accompanying drawings of this invention are intended to cover non-exclusive inclusion. For example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are explicitly listed, but may include other steps or units that are not explicitly listed or that are inherent to such processes, methods, products or devices.

[0044] It should be noted that, unless otherwise specified, the embodiments and features described in the present invention can be combined with each other. The present invention will now be described in detail with reference to the accompanying drawings and embodiments.

[0045] It should be noted that the acquisition, storage, use, and processing of data in the technical solution of this application all comply with the relevant provisions of national laws and regulations.

[0046] It should be noted that the iris-based identity recognition method and device of the present invention can be used in the financial field, or in any field other than the financial field. The application field of the iris-based identity recognition method and device of the present invention is not limited.

[0047] This invention incorporates iris template security into the considerations of iris recognition systems and constructs a highly reliable iris recognition scheme based on iris templates doped with false features. This scheme has higher reliability in resisting template information theft.

[0048] Figure 1 This is a flowchart of the iris-based identity recognition method according to an embodiment of the present invention, as follows: Figure 1 As shown, in one embodiment of the present invention, the iris-based identity recognition method of the present invention includes steps S101 to S104.

[0049] Step S101: Obtain the customer's iris image.

[0050] Step S102: Input the iris image into a preset feature extraction model to obtain the iris features extracted by the feature extraction model. The iris features extracted by the feature extraction model include real features and false features. The feature extraction model includes a first neural network and a second neural network. The first neural network extracts real features from the iris image, and the second neural network extracts false features from the iris image.

[0051] In this invention, a feature extraction model extracts multiple iris features. The feature extraction model combines the real features extracted from the iris image by a first neural network and the spurious features extracted from the iris image by a second neural network to output the iris features.

[0052] In this invention, the first neural network is trained based on iris images used for model training and is capable of accurately identifying iris features in the images.

[0053] In this invention, the first neural network is trained based on fake iris images and cannot identify the real iris features in the images; it can only identify the fake features.

[0054] Step S103: Obtain the encryption function corresponding to each iris template in the iris template library. The iris template contains iris features, which include real features and fake features. The encryption function is established based on all real features in the corresponding iris template and can be decrypted by any real feature in the corresponding iris template.

[0055] In this invention, the iris template specifically includes the customer's identity information and the customer's iris features. When the customer enters information, the iris image and the customer's identity information are collected. The iris image is then input into a feature extraction model to extract the iris features. Finally, the customer's iris template is created based on the iris features and the customer's identity information.

[0056] Specifically, for example, an iris template contains 7 iris features (A, B, C, D, E, F, G), where features E, F, and G are false features, and features A, B, C, and D are real features. This invention establishes an encryption function corresponding to the iris template based on the four real features A, B, C, and D. The established encryption function can be decrypted by any one of the four features A, B, C, and D.

[0057] Step S104: By using the iris features extracted by the feature extraction model to attempt to decrypt each encryption function, the iris template matching the customer is determined, thereby determining the customer's identity information.

[0058] Therefore, this invention improves the iris template by adding fake features to the iris characteristics, resulting in a mixture of real and fake features. Thus, even if the iris template is stolen, criminals will only obtain iris characteristics mixed with fake features. Since criminals cannot distinguish between real and fake features, they cannot obtain the customer's true iris characteristics even if they steal the iris template. Therefore, this invention effectively protects the iris template and improves the security of the customer's iris information.

[0059] like Figure 2 As shown, in one embodiment of the present invention, step S104 above attempts to decrypt each encryption function by using the iris features extracted by the feature extraction model to determine the iris template that matches the customer, thereby determining the customer's identity information. Specifically, it includes steps S201 and S202.

[0060] Step S201: By using the iris features extracted by the feature extraction model, attempt to decrypt each encryption function to determine the target encryption function, wherein the target encryption function is the encryption function with the most decryptable features among the iris features extracted by the feature extraction model.

[0061] Specifically, for example, an iris template contains 7 iris features (A, B, C, D, E, F, G). This invention uses these 7 iris features to attempt decryption for each encryption function. The decryption result is that features A, B, C, and D among these 7 iris features can decrypt encryption function A, but for other functions besides encryption function A, these 7 iris features cannot decrypt or only one feature can decrypt. In this case, encryption function A is determined as the standard encryption function.

[0062] Step S202: Determine the iris template corresponding to the target encryption function as the iris template that matches the customer, and then determine the customer's identity information based on the iris template that matches the customer.

[0063] In this invention, the iris template also contains the customer's identity information. After determining the iris template that matches the customer, the invention extracts the customer's identity information from the matched iris template.

[0064] like Figure 3 As shown, in one embodiment of the present invention, step S104 above attempts to decrypt each encryption function by using the iris features extracted by the feature extraction model to determine the iris template that matches the customer, thereby determining the customer's identity information, specifically including steps S301 to S303.

[0065] Step S301: By using the iris features extracted by the feature extraction model, attempt to decrypt each encryption function to determine the real features among the iris features extracted by the feature extraction model, wherein the real features are the iris features extracted by the feature extraction model that can decrypt the encryption functions.

[0066] Specifically, for example, an iris template contains seven iris features (A, B, C, D, E, F, G). This invention uses these seven iris features to attempt decryption for each encryption function. The decryption result is that features A, B, C, and D among these seven iris features can decrypt encryption function A, but for other functions besides encryption function A, these seven iris features cannot decrypt or only one feature can decrypt. In this case, features A, B, C, and D are determined as the true features.

[0067] Step S302: Calculate the similarity between the determined real features and the iris features of each iris template.

[0068] In an optional embodiment of the present invention, the present invention may employ any existing similarity calculation method to perform similarity calculation, such as using a cosine similarity algorithm to calculate cosine similarity.

[0069] Step S303: If the maximum similarity value is greater than a preset threshold, the iris template corresponding to the maximum similarity value is determined as the iris template matching the customer, and then the customer's identity information is determined based on the iris template matching the customer.

[0070] In this invention, the iris template also contains the customer's identity information. After determining the iris template that matches the customer, the invention extracts the customer's identity information from the matched iris template.

[0071] Figure 4 This is a schematic diagram of the model training process according to an embodiment of the present invention, as shown below. Figure 4 As shown, the specific training process of the feature extraction model in step S102 includes steps S401 to S403.

[0072] Step S401: Obtain training samples, wherein the training samples include: iris images used for model training and fake iris images generated based on the iris images used for model training.

[0073] In one embodiment of the present invention, the fake iris image is specifically obtained by splicing the iris image used for model training with at least one other iris image.

[0074] Step S402: Train the feature extraction model based on the training samples. During training, the iris image used for model training is input into the first neural network to train the first neural network, and the fake iris image is input into the second neural network to train the second neural network.

[0075] In one embodiment of the present invention, a first neural network is used to extract N features, and a second neural network is used to extract M features, where M is less than N.

[0076] In this invention, since the second neural network is trained from fake iris images, the second neural network cannot identify real iris features, and all outputs of the second neural network are fake features.

[0077] In one embodiment of the present invention, when training the feature extraction model, a first loss function is used to train the first neural network, and a second loss function is used to train the second neural network. The second loss function is the reciprocal of the first loss function. To ensure that the outputs of the second neural network are all false features, the loss function used by the second neural network is the reciprocal of the loss function used by the first neural network. The loss function used by the first neural network is intended to make the recognition result approach the true features, while using the reciprocal method makes the recognition result of the second neural network deviate from the true features.

[0078] Step S403: Based on the real features extracted by the first neural network from the iris image used for model training and the fake features extracted by the second neural network from the fake iris image, an iris template is established.

[0079] In one embodiment of the present invention, the model training process of the present invention further includes the following steps:

[0080] An encryption function is established based on the real features extracted from the iris image used for model training by the first neural network, and a correspondence is set between the established encryption function and the established iris template.

[0081] This invention establishes an iris template and a corresponding encryption function at the same time, and stores the correspondence between the two in a data table for easy retrieval later.

[0082] It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions, and although a logical order is shown in the flowchart, in some cases the steps shown or described may be executed in a different order than that shown here.

[0083] Based on the same inventive concept, embodiments of the present invention also provide an iris-based identity recognition device, which can be used to implement the iris-based identity recognition method described in the above embodiments, as described in the following embodiments. Since the principle of the iris-based identity recognition device in solving the problem is similar to that of the iris-based identity recognition method, embodiments of the iris-based identity recognition device can refer to embodiments of the iris-based identity recognition method, and repeated details will not be repeated. As used below, the terms "unit" or "module" can refer to a combination of software and / or hardware that implements a predetermined function. Although the device described in the following embodiments is preferably implemented in software, hardware implementation, or a combination of software and hardware, is also possible and contemplated.

[0084] Figure 5 This is a structural block diagram of an iris-based identity recognition device according to an embodiment of the present invention, as shown below. Figure 5 As shown, in one embodiment of the present invention, the iris-based identity recognition device of the present invention includes:

[0085] Iris image acquisition unit 1 is used to acquire the customer's iris image;

[0086] Iris feature extraction unit 2 is used to input the iris image into a preset feature extraction model to obtain the iris features extracted by the feature extraction model. The iris features extracted by the feature extraction model include real features and false features. The feature extraction model includes: a first neural network and a second neural network. The first neural network extracts real features from the iris image, and the second neural network extracts false features from the iris image.

[0087] Encryption function acquisition unit 3 is used to acquire the encryption function corresponding to each iris template in the iris template library. The iris template contains iris features, and the iris features in the iris template include real features and fake features. The encryption function is established based on all real features in the corresponding iris template, and the encryption function can be decrypted by any real feature in the corresponding iris template.

[0088] The identity recognition unit 4 is used to decrypt each encryption function by using the iris features extracted by the feature extraction model to determine the iris template that matches the customer, thereby determining the customer's identity information.

[0089] In one embodiment of the present invention, the identity recognition unit 4 specifically includes:

[0090] The target encryption function determination module is used to attempt to decrypt each encryption function using the iris features extracted by the feature extraction model, and determine the target encryption function, wherein the target encryption function is the encryption function with the most decryptable features among the iris features extracted by the feature extraction model among the encryption functions;

[0091] The first identity information determination module is used to determine the iris template corresponding to the target encryption function as the iris template that matches the customer, and then determine the customer's identity information based on the iris template that matches the customer.

[0092] In another embodiment of the present invention, the identity recognition unit 4 specifically includes:

[0093] The real feature determination module is used to attempt to decrypt each encryption function using the iris features extracted by the feature extraction model, and to determine the real features among the iris features extracted by the feature extraction model, wherein the real features are the iris features extracted by the feature extraction model that can decrypt the encryption functions;

[0094] The similarity calculation module is used to calculate the similarity between the determined real features and the iris features of each iris template;

[0095] The second identity information determination module is used to determine the iris template corresponding to the maximum similarity value as the iris template matching the customer if the maximum similarity value is greater than a preset threshold, and then determine the customer's identity information based on the iris template matching the customer.

[0096] In one embodiment of the present invention, the iris-based identity recognition device of the present invention further includes:

[0097] A training sample acquisition unit is used to acquire training samples, wherein the training samples include: an iris image used for model training and a fake iris image generated based on the iris image used for model training;

[0098] The training unit is used to train the feature extraction model based on the training samples. During training, the iris image used for model training is input into the first neural network to train the first neural network, and the fake iris image is input into the second neural network to train the second neural network.

[0099] The iris template establishment unit is used to establish an iris template based on the real features extracted by the first neural network from the iris image used for model training and the fake features extracted by the second neural network from the fake iris image.

[0100] In one embodiment of the present invention, the iris-based identity recognition device of the present invention further includes:

[0101] The encryption function establishment unit is used to establish an encryption function based on the real features extracted from the iris image used for model training by the first neural network, and to set a correspondence between the established encryption function and the established iris template.

[0102] To achieve the above objectives, according to another aspect of this application, a computer device is also provided. For example... Figure 6 As shown, the computer device includes a memory, a processor, a communication interface, and a communication bus. The memory stores a computer program that can run on the processor. When the processor executes the computer program, it implements the steps in the method of the above embodiments.

[0103] The processor can be a central processing unit (CPU). The processor can also be other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, or combinations of the above types of chips.

[0104] Memory, as a non-transitory computer-readable storage medium, can be used to store non-transitory software programs, non-transitory computer-executable programs, and units, such as the program units corresponding to the above-described method embodiments of the present invention. The processor executes various functional applications and data processing of the processor by running the non-transitory software programs, instructions, and modules stored in the memory, thereby implementing the methods described in the above-described method embodiments.

[0105] The memory may include a program storage area and a data storage area. The program storage area may store the operating system and applications required for at least one function; the data storage area may store data created by the processor, etc. Furthermore, the memory may include high-speed random access memory and non-transitory memory, such as at least one disk storage device, flash memory device, or other non-transitory solid-state storage device. In some embodiments, the memory may optionally include memory remotely located relative to the processor, which can be connected to the processor via a network. Examples of such networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.

[0106] The one or more units are stored in the memory and, when executed by the processor, perform the methods described in the above embodiments.

[0107] The specific details of the aforementioned computer equipment can be understood by referring to the relevant descriptions and effects in the above embodiments, and will not be repeated here.

[0108] To achieve the above objectives, according to another aspect of this application, a computer-readable storage medium is also provided, which stores a computer program that, when executed in a computer processor, implements the steps in the iris-based identity recognition method described above. Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The program can be stored in a computer-readable storage medium, and when executed, it can include the processes of the embodiments of the methods described above. The storage medium can be a magnetic disk, optical disk, read-only memory (ROM), random access memory (RAM), flash memory, hard disk drive (HDD), or solid-state drive (SSD), etc.; the storage medium may also include combinations of the above types of memory.

[0109] To achieve the above objectives, according to another aspect of this application, a computer program product is also provided, including a computer program / instructions that, when executed by a processor, implement the steps of the iris-based identity recognition method described above.

[0110] Obviously, those skilled in the art will understand that the modules or steps of the present invention described above can be implemented using general-purpose computing devices. They can be centralized on a single computing device or distributed across a network of multiple computing devices. Optionally, they can be implemented using computer-executable program code, thereby storing them in a storage device for execution by a computing device, or fabricating them separately as individual integrated circuit modules, or fabricating multiple modules or steps as a single integrated circuit module. Thus, the present invention is not limited to any particular hardware and software combination.

[0111] The above description is merely a preferred embodiment of the present invention and is not intended to limit the invention. Various modifications and variations can be made to the present invention by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. An iris-based identity recognition method, characterized in that, include: Obtain the customer's iris image; The iris image is input into a preset feature extraction model to obtain the iris features extracted by the feature extraction model. The iris features extracted by the feature extraction model include real features and false features. The feature extraction model includes a first neural network and a second neural network. The first neural network extracts real features from the iris image, and the second neural network extracts false features from the iris image. Obtain the encryption function corresponding to each iris template in the iris template library. The iris template contains iris features, which include real features and fake features. The encryption function is established based on all real features in the corresponding iris template and can be decrypted by any real feature in the corresponding iris template. By using the iris features extracted by the feature extraction model to attempt to decrypt each encryption function, an iris template matching the customer is determined, thereby determining the customer's identity information; By attempting to decrypt various encryption functions using the iris features extracted by the aforementioned feature extraction model, an iris template matching the customer is determined, thereby identifying the customer's identity information, specifically including: By using the iris features extracted by the feature extraction model to attempt to decrypt each encryption function, the true features in the iris features extracted by the feature extraction model are determined. The true features are the iris features extracted by the feature extraction model that can decrypt the encryption function. Calculate the similarity between the determined true features and the iris features of each iris template; If the maximum similarity value is greater than a preset threshold, the iris template corresponding to the maximum similarity value is determined as the iris template that matches the customer, and then the customer's identity information is determined based on the iris template that matches the customer.

2. The iris-based identity recognition method according to claim 1, characterized in that, By attempting to decrypt various encryption functions using the iris features extracted by the aforementioned feature extraction model, an iris template matching the customer is determined, thereby identifying the customer's identity information, specifically including: By using the iris features extracted by the feature extraction model to attempt to decrypt each encryption function, the target encryption function is determined. The target encryption function is the encryption function with the most decryptable features among the iris features extracted by the feature extraction model. The iris template corresponding to the target encryption function is determined as the iris template that matches the customer, and then the customer's identity information is determined based on the iris template that matches the customer.

3. The iris-based identity recognition method according to claim 1, characterized in that, Also includes: Obtain training samples, wherein the training samples include: iris images used for model training and fake iris images generated based on the iris images used for model training; The feature extraction model is trained based on the training samples. During training, the iris image used for model training is input into the first neural network to train the first neural network, and the fake iris image is input into the second neural network to train the second neural network. An iris template is established based on the real features extracted from the iris image used for model training by the first neural network and the fake features extracted from the fake iris image by the second neural network.

4. The iris-based identity recognition method according to claim 3, characterized in that, Also includes: An encryption function is established based on the real features extracted from the iris image used for model training by the first neural network, and a correspondence is set between the established encryption function and the established iris template.

5. The iris-based identity recognition method according to claim 2, characterized in that, A fake iris image is specifically obtained by stitching together the iris image used for model training with at least one other iris image.

6. The iris-based identity recognition method according to claim 1, characterized in that, When training the feature extraction model, the first neural network is trained using a first loss function, and the second neural network is trained using a second loss function, wherein the second loss function is the reciprocal of the first loss function.

7. An iris-based identity recognition device, characterized in that, include: Iris image acquisition unit, used to acquire the customer's iris image; An iris feature extraction unit is used to input the iris image into a preset feature extraction model to obtain iris features extracted by the feature extraction model. The iris features extracted by the feature extraction model include real features and false features. The feature extraction model includes a first neural network and a second neural network. The first neural network extracts real features from the iris image, and the second neural network extracts false features from the iris image. The encryption function acquisition unit is used to acquire the encryption function corresponding to each iris template in the iris template library. The iris template contains iris features, which include real features and fake features. The encryption function is established based on all real features in the corresponding iris template, and the encryption function can be decrypted by any real feature in the corresponding iris template. The identity recognition unit is used to decrypt each encryption function by using the iris features extracted by the feature extraction model to determine the iris template that matches the customer, thereby determining the customer's identity information; The identity recognition unit specifically includes: The real feature determination module is used to attempt to decrypt each encryption function using the iris features extracted by the feature extraction model, and to determine the real features among the iris features extracted by the feature extraction model, wherein the real features are the iris features extracted by the feature extraction model that can decrypt the encryption functions; The similarity calculation module is used to calculate the similarity between the determined real features and the iris features of each iris template; The second identity information determination module is used to determine the iris template corresponding to the maximum similarity value as the iris template matching the customer if the maximum similarity value is greater than a preset threshold, and then determine the customer's identity information based on the iris template matching the customer.

8. A computer device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 6.

9. A computer-readable storage medium having a computer program / instructions stored thereon, characterized in that, When the computer program / instructions are executed by the processor, they implement the steps of the method according to any one of claims 1 to 6.

10. A computer program product comprising a computer program / instructions, characterized in that, When the computer program / instructions are executed by the processor, they implement the steps of the method according to any one of claims 1 to 6.

Images