Method, device, computing equipment and medium for recognizing iris images

Abstract

The present disclosure provides a method for identifying iris images, which can be used in information security or other fields. The method includes: obtaining an iris image to be identified; extracting iris texture feature data of the iris image to be identified using a preset filter; determining multiple slice data based on the iris texture feature data; encrypting the multiple slice data to obtain multiple ciphertext slice data; sending the multiple ciphertext slice data to a server device, so that the server device generates a recognition result for the iris image to be identified based on the multiple ciphertext slice data; and receiving the recognition result from the server device. The present disclosure also provides a device for identifying an iris image, another method for identifying an iris image, another device for identifying an iris image, a computing device, a computer storage medium, and a computer program product.

Description

Technical Field

[0001] The present disclosure relates to the field of information security, and more specifically, to a method and apparatus for recognizing an iris image, a computing device, a computer storage medium, and a computer program product. Background Art

[0002] Iris recognition has the characteristics of uniqueness, stability, non-replicability, and liveness detection. Its comprehensive security performance has certain advantages among all types of biometric features. After decades of development, iris recognition technology has become increasingly mature and has been applied in more and more industries. However, with the expansion of the application scope of iris recognition technology, the amount of iris texture feature data identified and collected has continued to increase. Under the general trend of increasingly stringent regulatory requirements, how to ensure the privacy and security of biometric data has become a major problem. Once the iris texture feature data is lost, leaked, or even maliciously used during the use of iris recognition technology across institutions, it can cause significant losses. Summary of the invention

[0003] One aspect of the present disclosure provides a method for identifying an iris image, comprising: obtaining an iris image to be identified; extracting iris texture feature data of the iris image to be identified using a preset filter; determining a plurality of slice data based on the iris texture feature data; encrypting the plurality of slice data to obtain a plurality of ciphertext slice data; sending the plurality of ciphertext slice data to a server device so that the server device generates a recognition result for the iris image to be identified based on the plurality of ciphertext slice data; and receiving the recognition result from the server device.

[0004] Optionally, the extracting iris texture feature data of the iris image to be identified by using a preset filter includes: normalizing the iris image to be identified; and extracting features of the normalized iris image to be identified by using the preset filter to obtain the iris texture feature data of the iris image to be identified.

[0005] Optionally, the preset filter is a two-dimensional Gabor filter; the method further comprises: generating the two-dimensional Gabor filter G according to the following formula:

[0006]

[0007] Wherein, (r0, θ0) is the center position of the two-dimensional Gabor filter, and r, θ, α, β, ω are position parameters.

[0008] Optionally, the multiple slice data include first slice data and second slice data; determining the multiple slice data according to the iris texture feature data includes: generating first slice data having the same dimension as the iris texture feature data based on the iris texture feature data according to a random generation algorithm; and performing a preset operation on the iris texture feature data and the first slice data to obtain second slice data having the same dimension as the iris texture feature data.

[0009] Optionally, the generating, according to a random generation algorithm and based on the iris texture feature data, first slice data having the same dimension as the iris texture feature data comprises: randomly determining a target operation according to the random generation algorithm; and performing the target operation on each element in the iris texture feature data, respectively, to obtain an operation result having the same dimension as the iris texture feature data as the first slice data.

[0010] Optionally, the preset operation is a difference operation; the preset operation is performed on the iris texture feature data and the first slice data to obtain second slice data having the same dimension as the iris texture feature data, including: calculating the difference between each element in the iris texture feature data and the element corresponding to the element in the first slice data, and obtaining multiple difference values ​​as the second slice data.

[0011] Optionally, the multiple ciphertext shard data include first ciphertext shard data and second ciphertext shard data; encrypting the multiple ciphertext shard data to obtain multiple ciphertext shard data includes: encrypting the first shard data according to a first encryption algorithm to obtain first ciphertext shard data, and encrypting the second shard data according to a second encryption algorithm to obtain second ciphertext shard data.

[0012] Optionally, acquiring the iris image to be identified includes: collecting an original iris image; performing iris liveness detection and / or image quality detection on the original iris image; and determining the original iris image that passes the iris liveness detection and / or image quality detection as the iris image to be identified.

[0013] Optionally, the method is applied to a client device.

[0014] Another aspect of the present disclosure provides a method for identifying an iris image, comprising: receiving a plurality of ciphertext slice data from a client device, wherein each of the plurality of ciphertext slice data contains texture feature information of an iris image to be identified; decrypting the plurality of ciphertext slice data to obtain a plurality of slice data; distributing the plurality of slice data to a plurality of computing nodes so as to identify the plurality of slice data through the plurality of computing nodes to obtain an identification result for the iris image to be identified; and sending the identification result to the client device.

[0015] Optionally, the multiple ciphertext fragment data include first ciphertext fragment data and second ciphertext fragment data; decrypting the multiple ciphertext fragment data to obtain multiple fragment data includes: decrypting the first ciphertext fragment data according to a first encryption algorithm to obtain first fragment data, and decrypting the second ciphertext fragment data according to a second encryption algorithm to obtain second fragment data.

[0016] Optionally, the distributing the multiple slice data to multiple computing nodes so as to identify the multiple slice data through the multiple computing nodes to obtain a recognition result for the iris image to be recognized includes: allocating a first computing node to the first slice data and allocating a second computing node to the second slice data; acquiring the first slice data through the first computing node and calculating a first similarity between the first slice data and a pre-stored iris feature; acquiring the second slice data through the second computing node and calculating a second similarity between the second slice data and a pre-stored iris feature; and determining the recognition result based on the first similarity and the second similarity.

[0017] Optionally, the method also includes: storing the first shard data in a first data cache space, and storing the second shard data in a second data cache space, wherein the first data cache space and the second data cache space belong to different management domains; wherein obtaining the first shard data through the first computing node includes: reading the first shard data in the first data cache space through the first computing node; obtaining the second shard data through the second computing node includes: reading the second shard data in the second data cache space through the second computing node.

[0018] Optionally, the method is applied to a server device.

[0019] Another aspect of the present disclosure provides an apparatus for identifying an iris image, comprising: an acquisition module for acquiring an iris image to be identified; an extraction module for extracting iris texture feature data of the iris image to be identified using a preset filter; a slicing module for determining a plurality of slicing data based on the iris texture feature data; an encryption module for encrypting the plurality of slicing data to obtain a plurality of ciphertext slicing data; a sending module for sending the plurality of ciphertext slicing data to a server device, so that the server device generates a recognition result for the iris image to be identified based on the plurality of ciphertext slicing data; and a first receiving module for receiving the recognition result from the server device.

[0020] Another aspect of the present disclosure provides an apparatus for identifying an iris image, comprising: a second receiving module, used to receive a plurality of ciphertext slice data from a client device, each of the plurality of ciphertext slice data containing texture feature information of an iris image to be identified; a decryption module, used to decrypt the plurality of ciphertext slice data to obtain a plurality of slice data; an identification module, used to distribute the plurality of slice data to a plurality of computing nodes so as to identify the plurality of slice data through the plurality of computing nodes to obtain an identification result for the iris image to be identified; and a sending module, used to send the identification result to the client device.

[0021] Another aspect of the present disclosure provides a computing device, including: one or more processors; a storage device for storing one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors implement the method as described above.

[0022] Another aspect of the present disclosure provides a computer-readable storage medium storing computer-executable instructions, which are used to implement the above method when executed.

[0023] Another aspect of the present disclosure provides a computer program, which includes computer executable instructions, and the instructions are used to implement the method described above when executed.

[0024] According to an embodiment of the present disclosure, the iris texture feature data of the iris image to be identified is sliced ​​by a client device to obtain a plurality of sliced ​​data, and then the plurality of sliced ​​data are encrypted, and the plurality of ciphertext sliced ​​data obtained after encryption are sent to a server device, so that the server device generates a recognition result for the iris image to be identified according to the plurality of ciphertext sliced ​​data. Even if the ciphertext sliced ​​data is stolen after decryption, the iris image will not be leaked, thereby achieving privacy protection for the application of iris recognition technology across institutions and technically improving the security and compliance of iris characteristic data. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] For a more complete understanding of the present disclosure and its advantages, reference will now be made to the following description taken in conjunction with the accompanying drawings, in which:

[0026] Figure 1 The system architecture of the method for recognizing an iris image and the device for recognizing an iris image according to an embodiment of the present disclosure is schematically shown;

[0027] Figure 2 The flowchart of the method for recognizing an iris image according to an embodiment of the present disclosure is schematically shown;

[0028] Figure 3 The flowchart of the method for recognizing an iris image according to an embodiment of the present disclosure is schematically shown;

[0029] Figure 4 A flowchart of a method for recognizing an iris image according to another embodiment of the present disclosure is schematically shown;

[0030] Figure 5 A block diagram schematically shows a device for recognizing an iris image according to an embodiment of the present disclosure;

[0031] Figure 6 A block diagram schematically shows an apparatus for recognizing an iris image according to another embodiment of the present disclosure;

[0032] Figure 7 A block diagram schematically illustrates a recognition module according to an embodiment of the present disclosure; and

[0033] Figure 8 The block diagram of a computer system suitable for implementing the method described above according to an embodiment of the present disclosure is schematically shown. DETAILED DESCRIPTION

[0034] Hereinafter, embodiments of the present disclosure will be described with reference to the accompanying drawings. However, it should be understood that these descriptions are exemplary only and are not intended to limit the scope of the present disclosure. In the following detailed description, for ease of explanation, many specific details are set forth to provide a comprehensive understanding of the embodiments of the present disclosure. However, it is apparent that one or more embodiments may also be implemented without these specific details. In addition, in the following description, descriptions of known structures and technologies are omitted to avoid unnecessary confusion of the concepts of the present disclosure.

[0035] The terms used herein are only for describing specific embodiments and are not intended to limit the present disclosure. The terms "comprise", "include", etc. used herein indicate the existence of the features, steps, operations and / or components, but do not exclude the existence or addition of one or more other features, steps, operations or components.

[0036] All terms (including technical and scientific terms) used herein have the meanings commonly understood by those skilled in the art, unless otherwise defined. It should be noted that the terms used herein should be interpreted as having a meaning consistent with the context of this specification, and should not be interpreted in an idealized or overly rigid manner.

[0037] When using expressions such as "at least one of A, B, and C, etc.", they should generally be interpreted according to the meaning of the expression commonly understood by those skilled in the art (for example, "a system having at least one of A, B, and C" should include but is not limited to a system having A alone, B alone, C alone, A and B, A and C, B and C, and / or A, B, C, etc.).

[0038] Some block diagrams and / or flow charts are shown in the accompanying drawings. It should be understood that some boxes or combinations thereof in the block diagrams and / or flow charts can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that these instructions can create a device for implementing the functions / operations described in these block diagrams and / or flow charts when executed by the processor. The technology of the present disclosure can be implemented in the form of hardware and / or software (including firmware, microcode, etc.). In addition, the technology of the present disclosure can take the form of a computer program product on a computer-readable storage medium storing instructions, which can be used by an instruction execution system or used in conjunction with an instruction execution system.

[0039] The present disclosure provides a method and device for recognizing iris images, which can achieve privacy protection in cross-institutional iris recognition application scenarios and technically improve the security and compliance of iris characteristic data.

[0040] The embodiments of the present disclosure provide a method for identifying an iris image and a device for identifying an iris image to which the method can be applied. The method includes obtaining an iris image to be identified; extracting iris texture feature data of the iris image to be identified using a preset filter; determining multiple slice data according to the iris texture feature data; encrypting the multiple slice data to obtain multiple ciphertext slice data; sending the multiple ciphertext slice data to a server device so that the server device generates a recognition result for the iris image to be identified according to the multiple ciphertext slice data; and receiving the recognition result from the server device.

[0041] It should be noted that the method and device for recognizing iris images according to the embodiments of the present disclosure can be used in the field of information security, and can also be used in any field other than information security. The present disclosure does not limit the application field of the method and device for recognizing iris images.

[0042] Figure 1 The system architecture of the method for recognizing an iris image and the device for recognizing an iris image according to an embodiment of the present disclosure is schematically shown. It should be noted that: Figure 1 The examples shown are merely scenarios in which the embodiments of the present disclosure can be applied, to help those skilled in the art understand the technical content of the present disclosure, but do not mean that the embodiments of the present disclosure cannot be used in other devices, systems, environments or scenarios.

[0043] like Figure 1 As shown, the system architecture 100 according to this embodiment may include a server device 110, a client device 120, and a network 130. The network 130 is used to provide a medium for a communication link between the client device 120 and the server device 110. The network 130 may include various connection types, such as wired, wireless communication links or optical fiber cables, etc.

[0044] The user can use the client device 120 to interact with the server device 110 through the network 130 to receive or send messages, etc. The client device 120 can be installed with client applications, such as online banking clients, shopping applications, web browser applications, search applications, instant messaging tools, email clients, social platform software, etc. (only as examples).

[0045] The client device 120 may be any electronic device having a display screen and supporting web browsing, including but not limited to a smart phone, a tablet computer, a laptop computer, a desktop computer, and the like.

[0046] The server device 110 may be a server that provides various services, such as a background management server that provides support for websites browsed by users using the client device 120 (only as an example). The background management server may analyze and process received data such as user requests, and feed back the processing results (such as web pages, information, or data obtained or generated according to user requests, etc.) to the terminal device. The server device 110 may schedule multiple computing nodes, each of which may be used to identify feature information in an iris image. It should be noted that the computing node may be set in the server device 110, or may be set in other devices other than the server device 110 that can interact with the server device 110, and the present disclosure does not specifically limit this. By way of example, in an embodiment of the present disclosure, the server device 110 may be a server deployed in the cloud.

[0047] In the disclosed embodiment, the client device 120, for example, has an iris image acquisition device 121, such as a near-infrared imaging device, for acquiring iris images. The client device 120 can drive the near-infrared imaging device 121 through a pre-installed SDK (software development kit) to complete iris image acquisition, and through the iris feature extraction, data slicing and encryption functions integrated in the SDK, complete the random slicing and encryption processing of the iris texture feature data, obtain multiple encrypted slicing data, and send these encrypted slicing data to the server device 110. After the server device 110 decrypts the received encrypted slicing data, it distributes the decrypted slicing data to different computing nodes for identification to obtain an identification result. Then the server device 110 returns the identification result to the client device 120.

[0048] According to the embodiments of the present disclosure, the client device 120 can be used as the data owner, and the server device 110 can be used as the technical service provider. The iris recognition privacy computing service can be deployed in the server device 110 for the client program in the client device 120 to call. The client program in the client device 120 can drive the video stream data collected by the camera device, obtain the iris image for feature extraction, slicing and encryption processing, and then call the iris recognition privacy computing service of the server device 110 to complete the decryption and slicing comparison processing, thereby realizing the entire iris recognition process and ensuring the privacy security of the iris information of the data owner.

[0049] It should be understood that Figure 1 The number of client devices, networks, and server devices in the embodiment is only illustrative. Any number of client devices, networks, and server devices may be provided as required.

[0050] Figure 2 The flowchart of the method for recognizing an iris image according to an embodiment of the present disclosure is schematically shown.

[0051] like Figure 2 As shown, the method includes operations S210 to S260. The method of the embodiment of the present disclosure may be performed by a client device, for example, the client device may be Figure 1 A client device 120 is shown.

[0052] In operation S210, an iris image to be recognized is acquired.

[0053] According to an embodiment of the present disclosure, the client device has an imaging device, such as a near-infrared imaging device, and an iris image of the object to be identified is collected by the imaging device.

[0054] According to an embodiment of the present disclosure, in order to improve the accuracy of recognition, iris liveness detection and / or image quality detection may be performed on the collected iris image, and iris images with poor effects may be screened out based on the detection results, and the original iris image that passes the iris liveness detection and / or image quality detection may be determined as the iris image to be identified. Among them, iris liveness detection is used to detect whether the iris image is collected from a living object. If it is detected that the iris image is collected from a living object, it is passed, otherwise it is failed. Image quality detection is used to detect the imaging effect of the iris image. If it is determined that the imaging effect meets the preset requirements, it is passed, otherwise it is failed, thereby screening out images with poor imaging effects. More specifically, the preset requirements may, for example, include that the degree of jitter, angle, size, brightness, etc. of the iris image are within a preset range.

[0055] In operation S220, iris texture feature data of the iris image to be recognized is extracted using a preset filter.

[0056] According to the embodiments of the present disclosure, the iris image to be identified may be normalized, and then a preset filter may be used to extract features of the normalized iris image to be identified to obtain iris texture feature data of the iris image to be identified.

[0057] The preset filter may be, for example, a two-dimensional Gabor filter. The two-dimensional Gabor filter G may be generated according to the following formula:

[0058]

[0059] Among them, (r0, θ0) is the center position of the two-dimensional Gabor filter, r, θ, α, β, ω are position parameters, and the center position and position parameters can be set according to actual needs. The two-dimensional Gabor filter has a good function of obtaining node positions in the spatial domain and frequency domain, and due to its good integral characteristics, the filter can obtain local phase information.

[0060] For example, in this embodiment, a complex-valued two-dimensional Gabor filter in polar coordinates can be used to process the normalized iris image using 1024 wavelets to obtain 2048-bit data, i.e., 256-byte encoding, as iris texture feature data. It can be understood that the iris texture feature data in this embodiment is 2048-dimensional.

[0061] In operation S230, a plurality of fragment data are determined according to the iris texture feature data.

[0062] According to an embodiment of the present disclosure, the fragmented data may be generated based on the iris texture feature data according to a random generation algorithm, wherein the number of the fragmented data is at least two.

[0063] Exemplarily, in this embodiment, the slice data may include first slice data and second slice data. The first slice data may be generated based on the iris texture feature data according to a random generation algorithm, and then a preset operation may be performed on the iris texture feature data and the first slice data to obtain the second slice data. The iris texture feature data, the first slice data, and the second slice data have the same dimension. The preset operation may be, for example, a difference operation. According to other embodiments of the present disclosure, the preset operation may also be other operations such as addition, multiplication, and division.

[0064] More specifically, a random operation can be randomly determined as a target operation according to a random generation algorithm, and then the target operation is performed for each element in the iris texture feature data to obtain a calculation result having the same dimension as the iris texture feature data as the first fragment data. Then, the difference between each element in the iris texture feature data and the element corresponding to the element in the first fragment data is calculated to obtain multiple difference values ​​as the second fragment data.

[0065] For example, the iris texture feature data is as follows:

[0066]

[0067] The target operation randomly determined by the random generation algorithm is multiplication by 2 and then subtraction by 1. Then, the operations of multiplication by 2 and then subtraction by 1 are performed on a1, a2, a3, and a4 respectively, and the first shard data is obtained as follows:

[0068]

[0069] Then, the difference between each element in the iris texture feature data and the element corresponding to the element in the first fragment data is calculated, that is, (2a1-1)-a1=a1-1, (2a2-1)-a2=a2-1... and so on, the second fragment data is obtained as follows:

[0070]

[0071] Those skilled in the art will appreciate that the above exemplary embodiments are only used to understand the present disclosure, and the present disclosure is not limited thereto.

[0072] According to the embodiments of the present disclosure, since the fragmented data is randomly generated based on the iris texture feature data, the iris texture feature data itself can be hidden while retaining the data features of the iris texture feature data, thereby improving the security of the data.

[0073] In operation S240, the plurality of slice data are encrypted to obtain a plurality of ciphertext slice data.

[0074] According to an embodiment of the present disclosure, according to a first encryption algorithm, the first shard data is encrypted to obtain first ciphertext shard data, and according to a second encryption algorithm, the second shard data is encrypted to obtain second ciphertext shard data. Among them, the first encryption algorithm and the second encryption algorithm can be symmetric encryption algorithms or asymmetric encryption algorithms. The first encryption algorithm and the second encryption algorithm can be the same algorithm or different algorithms. Exemplarily, in this embodiment, the first encryption algorithm and the second encryption algorithm are the same symmetric encryption algorithm, and the symmetric encryption algorithm can be, for example, the Zu Chongzhi algorithm (ZUC algorithm) that complies with the national encryption standard.

[0075] In operation S250, the plurality of ciphertext fragment data are sent to the server device, so that the server device generates a recognition result for the iris image to be recognized according to the plurality of ciphertext fragment data.

[0076] According to an embodiment of the present disclosure, the client device may send a plurality of ciphertext fragmented data to the server device, and the server device may generate a recognition result for the iris image to be recognized based on the plurality of ciphertext fragmented data.

[0077] In operation S260, a recognition result is received from the server device.

[0078] According to an embodiment of the present disclosure, after the server device generates the recognition result, the generated recognition result can be sent from the server device to the client device, and correspondingly, the recognition result from the server device can be received by the client device.

[0079] According to an embodiment of the present disclosure, the iris texture feature data of the iris image to be identified is sliced ​​by a client device to obtain multiple sliced ​​data, and then the multiple sliced ​​data are encrypted, and the multiple ciphertext sliced ​​data obtained after encryption are sent to a server device, so that the server device generates a recognition result for the iris image to be identified based on the multiple ciphertext sliced ​​data. Even if the ciphertext sliced ​​data is stolen after decryption, the iris image will not be leaked, thereby achieving privacy protection for the application of iris recognition technology across institutions and technically improving the security and compliance of iris characteristic data.

[0080] Figure 3 The flowchart of the method for recognizing an iris image according to an embodiment of the present disclosure is schematically shown.

[0081] like Figure 3 As shown, the method includes operations S310 to S340. The method of the embodiment of the present disclosure may be executed by a server device, for example, the server device may be Figure 1 The server device 110 is shown.

[0082] In operation S310, a plurality of ciphertext fragment data is received from a client device.

[0083] According to an embodiment of the present disclosure, each of the received plurality of ciphertext fragment data contains texture feature information of the iris image to be identified.

[0084] In operation S320, the plurality of ciphertext fragmented data are decrypted to obtain a plurality of fragmented data.

[0085] According to an embodiment of the present disclosure, the first ciphertext shard data can be decrypted according to a first encryption algorithm to obtain first shard data, and the second ciphertext shard data can be decrypted according to a second encryption algorithm to obtain second shard data.

[0086] In operation S330, the plurality of slice data are distributed to a plurality of computing nodes, so that the plurality of slice data are recognized by the plurality of computing nodes to obtain a recognition result for the iris image to be recognized.

[0087] According to an embodiment of the present disclosure, a first computing node may be allocated to the first shard data, and a second computing node may be allocated to the second shard data. Then, the first shard data may be acquired through the first computing node, and a first similarity between the first shard data and the pre-stored iris feature may be calculated. The second shard data may be acquired through the second computing node, and a second similarity between the second shard data and the pre-stored iris feature may be calculated. Next, a recognition result may be determined based on the first similarity and the second similarity.

[0088] According to an embodiment of the present disclosure, the pre-stored iris features are pre-recorded iris features of the user. Exemplarily, in this embodiment, texture features extracted from the iris image entered by the user during registration can be used as pre-stored iris features and stored in the database.

[0089] For example, in this embodiment, when both the first similarity and the second similarity are greater than the similarity threshold, the recognition result is determined to be feature-compliant, and when either the first similarity or the second similarity is less than or equal to the similarity threshold, the recognition result is determined to be feature-uncompliant. The similarity threshold can be determined according to actual needs, and this disclosure does not specifically limit this.

[0090] According to an embodiment of the present disclosure, the first shard data can be stored in the first data cache space, and the second shard data can be stored in the second data cache space, wherein the first data cache space and the second data cache space belong to different management domains. Since the first shard data and the second shard data are stored in different management domains, even if the data in a certain management domain is stolen by others, since only a single shard data is stored in the management domain, the thief cannot restore the original data, and the security is higher.

[0091] Based on this, the first shard data in the first data cache space can be read by the first computing node to obtain the first shard data, and the second shard data in the second data cache space can be read by the second computing node to obtain the second shard data.

[0092] In operation S340 , the recognition result is sent to the client device.

[0093] Related technologies use methods of transforming the original plaintext image and fully encrypting the iris image to achieve privacy protection for iris recognition in cross-institutional application scenarios. For the method of transforming the original plaintext image, the original features of the image are changed during the transformation of the original plaintext image, so that the biometric feature values ​​extracted by the iris recognition algorithm are affected, thereby affecting the recognition accuracy and even making the extracted features unusable for iris recognition. For the method of fully encrypting the iris image, although this method improves the security of the iris feature image during transmission, the iris image must be decrypted before the iris recognition algorithm is executed to complete the iris recognition feature extraction, and in the event of an external attack, the decrypted iris image is still at risk of being leaked.

[0094] According to the embodiment of the present disclosure, the server device decrypts the received multiple ciphertext fragmented data to obtain multiple fragmented data, and then distributes the multiple fragmented data to multiple computing nodes, and multiple computing nodes identify the multiple fragmented data to obtain the recognition result for the iris image to be recognized. In this process, the fragmented data are isolated from each other, and because the fragmented data hides the iris feature data, even if the decrypted fragmented data is lost, it will not cause the iris feature to be leaked, thereby improving the security of the iris texture feature data and protecting the user's privacy data.

[0095] Reference below Figure 4 , combined with specific embodiments Figure 2 The method shown is further explained.

[0096] Those skilled in the art will appreciate that the following exemplary embodiments are only used to understand the present disclosure, and the present disclosure is not limited thereto.

[0097] Figure 4 The flowchart of a method for recognizing an iris image according to another embodiment of the present disclosure is schematically shown.

[0098] like Figure 4 As shown, the method may include, for example, the following steps S401 to S411.

[0099] In step S401, the client device collects an iris image.

[0100] According to the embodiments of the present disclosure, the client device can drive the near-infrared imaging device to collect and generate a complete iris original image that meets the standard after passing the iris liveness detection and image quality detection. This collection function is compatible with iris near-infrared imaging devices from different manufacturers.

[0101] In step S402, the client device extracts iris texture feature data from the original iris image collected in step S401 using an iris feature extraction algorithm.

[0102] According to the embodiment of the present disclosure, a complex-valued two-dimensional Gabor filter under polar coordinates can be used to extract the features of iris details from the normalized iris image, and 1024 wavelets are used to process the image to obtain 2048-bit data, that is, 256-byte encoding, as iris texture feature data. It can be understood that the iris texture feature data in this embodiment is a 2048-dimensional feature vector. For the convenience of description, the feature vector is called feature vector A.

[0103] In step S403, the client device divides the iris texture feature data into random fragment data using a fragmentation algorithm.

[0104] According to the embodiments of the present disclosure, the 2048-dimensional feature vector A extracted from the original plaintext image of the iris can be sliced ​​to generate random iris feature slice data. Exemplarily, in this embodiment, the feature vector element random difference processing is adopted to generate a random sequence of iris features. More specifically, according to the number of dimensions of the feature vector A, a random vector B corresponding to a 2048-dimensional length can be generated by a random function, and each element of the two can be subjected to a difference operation to obtain a 2048-dimensional vector C. Since the generation of the random vector B is random and the value is different each time, even if it is the iris feature data of the same person, the eigenvalues ​​of the vector C will be different in different usage scenarios. Therefore, two iris feature random slice data, feature vector B and feature vector C, can be generated according to the feature vector A extracted from the original image.

[0105] In step S404, the client device encrypts the data slices using an encryption algorithm to obtain ciphertext slice data.

[0106] According to the embodiment of the present disclosure, the iris feature random slice data is encrypted to achieve confidentiality protection transmission of the iris feature slice data. Exemplarily, in this embodiment, a symmetric encryption algorithm is used to encrypt the slice data into ciphertext, and the symmetric encryption algorithm uses the ZUC algorithm that complies with the national encryption standard.

[0107] In step S405, the client device sends the encrypted segment data to the server device in the cloud.

[0108] In step S406, the server device receives the iris feature encrypted fragment data sent by the client device.

[0109] In step S407, the server device calls the symmetric encryption key to decrypt the received ciphertext fragmented data and restore it to iris feature random fragmented data.

[0110] According to an embodiment of the present disclosure, the server-side device uses a symmetric encryption algorithm corresponding to the client device to decrypt the ciphertext fragments and restore them to iris feature random fragment data.

[0111] According to the embodiments of the present disclosure, the server device can send the encrypted shard data to the partner databases belonging to different management domains. Since the same management domain only controls part of the shards, any participant cannot restore the iris feature value without obtaining the shard data of other participants, thereby enhancing data security.

[0112] In step S408, the server device routes the shard data to the corresponding computing node.

[0113] According to an embodiment of the present disclosure, after the decrypted iris feature random sharding data is sent to the data cache space belonging to different management domains respectively, it can be forwarded to the algorithm computing node of iris recognition and comparison according to the route specified by the task scheduling, and the registered and identified iris feature random sharding data can be used as the data input of the respective computing nodes.

[0114] In step S409, the server-side device starts the iris recognition comparison algorithm operation through the cloud computing node, uses the registered iris feature segment data and the received on-site iris feature segment data as data inputs of the respective computing nodes, and collaboratively completes the iris feature comparison calculation to obtain the recognition result.

[0115] According to the embodiments of the present disclosure, according to the needs of iris recognition computing tasks, multiple iris recognition computing nodes in different management domains can be coordinated and scheduled to start collaborative computing tasks, and the cosine distance can be used as a method to judge the similarity of two sets of features to complete the operation of random slice data of iris feature vectors of on-site iris photos (iris images to be identified collected on-site) and random slice data of iris feature vectors of registered iris photos (iris photos collected during registration). When the similarity between the two is greater than a set threshold, it is considered that the on-site iris photo and the registered iris photo belong to the same person, and the final iris feature comparison operation result is returned after the calculation is completed.

[0116] In step S410, the server device returns the recognition result to the client device in real time.

[0117] In step S411 , the client device receives the recognition result.

[0118] According to the embodiments of the present disclosure, the client device drives the near-infrared imaging device through the SDK of the client software to complete iris image acquisition, and completes the random sharding and encryption of iris texture feature data through the iris feature extraction, data sharding and encryption functions integrated in the client SDK, and cooperates with the iris recognition privacy computing service in the cloud to realize iris recognition service with privacy protection function.

[0119] The method for identifying iris images according to the embodiments of the present disclosure can achieve privacy protection for the application of iris recognition technology across institutions. Based on this method, under the premise of no trusted third-party management and no reliance on specific hardware equipment, the data owner can technically ensure that the privacy of the user's iris information is protected when using the iris recognition service of an external technical service provider, and prevent the leakage of iris information data during the cross-institutional circulation process. More specifically, this method has advantages in at least the following methods.

[0120] First, it can protect the legitimate rights and interests of users. According to the embodiments of the present disclosure, the user's iris information is converted into iris feature random sharding data or ciphertext data during the registration, transmission and identification process, and is distributed in different management nodes for storage and collaborative calculation, thereby ensuring that users can obtain convenient iris recognition and authentication services while their personal privacy is not violated.

[0121] Second, it can improve the operating efficiency of the data owner. According to the embodiments of the present disclosure, the data owner, as the subject of personal biometric information collection, can effectively manage the data usage and scope of the user's personal iris information, provide users with convenient and safe intelligent services, enhance customer acquisition and activation capabilities, improve business performance, and at the same time, implement personal information security protection responsibilities and meet regulatory compliance requirements.

[0122] Third, it can expand the service boundaries of technical service providers. According to the method of recognizing iris images in the embodiments of the present disclosure, the technical means of privacy protection of iris recognition is improved, and the user's concerns about the leakage of collected irises are eliminated. It can promote the promotion of iris recognition technology providers to more partner scenarios, thereby driving more companies to upgrade to intelligentization and improve the scope and quality of service output.

[0123] Figure 5 The block diagram schematically shows a device for recognizing an iris image according to an embodiment of the present disclosure.

[0124] like Figure 5 As shown, the apparatus 500 for recognizing an iris image includes an acquisition module 510, an extraction module 520, a segmentation module 530, an encryption module 540, a sending module 550 and a first receiving module 560. The apparatus 500 for recognizing an iris image can execute the above reference Figure 2 Describe the method.

[0125] Specifically, the acquisition module 510 can be used to acquire an iris image to be recognized.

[0126] The extraction module 520 may be used to extract iris texture feature data from the iris image to be identified by using an iris feature extraction algorithm.

[0127] The fragmentation module 530 may be used to determine a plurality of fragmentation data according to the iris texture feature data.

[0128] The encryption module 540 can be used to encrypt multiple fragmented data to obtain multiple ciphertext fragmented data.

[0129] The sending module 550 may be used to send a plurality of ciphertext fragmented data to a server device, so that the server device generates a recognition result for the iris image to be recognized according to the plurality of ciphertext fragmented data.

[0130] The first receiving module 560 may be configured to receive a recognition result from a server device.

[0131] For example, in this embodiment, the acquisition module 510 can be specifically used to collect the original plaintext image of the iris. Encapsulate the iris image acquisition SDK, drive the near-infrared imaging device, obtain the user's iris image, and after iris liveness detection and image quality detection, obtain the front image that meets the iris recognition requirements and generate the entire iris plaintext image.

[0132] For example, in this embodiment, the extraction module 520 can be used to extract the features of iris details from the normalized iris image using a complex-valued two-dimensional Gabor filter under polar coordinates, and use 1024 wavelets to process the image to obtain 2048-bit data, that is, 256-byte encoding, as iris texture feature data. It can be understood that the iris texture feature data in this embodiment is a 2048-dimensional feature vector. For the convenience of description, the feature vector is referred to as feature vector A.

[0133] Exemplarily, in this embodiment, the slicing module 530 can be used to slice the 2048-dimensional feature vector A extracted from the original plaintext image of the iris to generate random slicing data of the iris feature. Exemplarily, in this embodiment, the random difference processing of the feature vector elements is adopted to generate a random sequence of iris features. More specifically, according to the number of dimensions of the feature vector A, a random vector B corresponding to a length of 2048 dimensions can be generated by a random function, and the difference operation is performed on each element of the two to obtain a 2048-dimensional vector C. Since the generation of the random vector B is random, the value is different each time. Even if it is the iris feature data of the same person, the eigenvalue of the vector C will be different in different usage scenarios. Therefore, two iris feature random slicing data of feature vector B and feature vector C can be generated according to the feature vector A extracted from the original image.

[0134] For example, in this embodiment, the extraction module 520 can be used to encrypt the random iris feature fragmentation data to achieve confidentiality protection transmission of the iris feature fragmentation data. The fragmentation data is encrypted into ciphertext using a symmetric encryption algorithm, and the symmetric encryption algorithm uses the ZUC algorithm that complies with the national encryption standard.

[0135] Figure 6 The following schematically shows a block diagram of an apparatus for recognizing an iris image according to another embodiment of the present disclosure.

[0136] like Figure 6 As shown, the apparatus 600 for recognizing an iris image includes a second receiving module 610, a decryption module 620, a recognition module 630 and a sending module 640. The apparatus 600 for recognizing an iris image can execute the above reference Figure 3 Describe the method.

[0137] Specifically, the second receiving module 610 may be configured to receive a plurality of ciphertext fragmented data from a client device, wherein each of the plurality of ciphertext fragmented data contains texture feature information of an iris image to be identified.

[0138] The decryption module 620 can be used to decrypt multiple ciphertext fragmented data to obtain multiple fragmented data.

[0139] The recognition module 630 may be used to distribute the plurality of slice data to the plurality of computing nodes, so as to recognize the plurality of slice data through the plurality of computing nodes and obtain a recognition result for the iris image to be recognized.

[0140] The sending module 640 may be configured to send the recognition result to the client device.

[0141] For example, in this embodiment, the decryption module 620 can be used to restore the ciphertext fragments of the iris feature into plaintext random fragment data. Specifically, the symmetric encryption algorithm corresponding to the client can be used to decrypt the ciphertext fragments and restore them into the iris feature random fragment data.

[0142] Figure 7 The block diagram of the recognition module according to the embodiment of the present disclosure is schematically shown.

[0143] like Figure 7 As shown, the identification module 630 may include, for example, a data access unit 731 , a multi-party secure computing unit 732 , and a task scheduling unit 733 .

[0144] The data access unit 731 can be used to receive and route the iris feature random sharding data restored by the decryption module 620, and distribute the feature data required for the iris recognition operation to the corresponding computing nodes. Specifically, the decrypted iris feature random sharding data is sent to the data cache space belonging to different management domains, and then forwarded to the algorithm computing node of iris recognition comparison according to the route specified by the task scheduling, and the registered and recognized iris feature random sharding data are used as the data input of each computing node.

[0145] The multi-party secure computing unit 732 can be used to complete the comparison operation of the randomly sharded data of the iris feature to ensure that the calculation result of the sharded data is consistent with the calculation result of the complete feature data, or the loss of precision of the result is within an acceptable range. Specifically, the multi-party secure computing unit can be divided into two parts: computing support and business computing logic. The computing support implements basic multi-party secure computing protocols such as secret sharing, homomorphic encryption, and obfuscated circuits, and encapsulates basic computing functions such as addition, subtraction, multiplication, division, and comparison, as well as other complex computing functions derived from basic computing functions. The business computing logic part contains the computing steps required to support the iris recognition business scenario, and each step completes the calculation of the iris texture feature data by calling the basic computing function and the derived computing function.

[0146] The task scheduling unit 733 can be used to implement task scheduling management between different computing nodes. According to the needs of iris recognition computing tasks, multiple iris recognition computing nodes in different management domains are coordinated to start collaborative computing tasks, and the cosine distance is used as a method to judge the similarity of two sets of features to complete the calculation of the random sharding data of the iris feature vector of the on-site photo and the random sharding data of the iris feature vector of the registered photo. When the similarity between the two is greater than the set threshold, it is considered that the on-site iris photo and the registered iris photo belong to the same person, and the final iris feature comparison calculation result is returned after the calculation is completed.

[0147] According to the embodiments of the present invention, any one or more of the modules, submodules, units, and subunits, or at least part of the functions of any one of them can be implemented in one module. According to the embodiments of the present invention, any one or more of the modules, submodules, units, and subunits can be split into multiple modules for implementation. According to the embodiments of the present invention, any one or more of the modules, submodules, units, and subunits can be at least partially implemented as hardware circuits, such as field programmable gate arrays (FPGAs), programmable logic arrays (PLAs), systems on chips, systems on substrates, systems on packages, application specific integrated circuits (ASICs), or can be implemented by hardware or firmware in any other reasonable way of integrating or packaging the circuit, or implemented in any one of the three implementation methods of software, hardware, and firmware, or in any appropriate combination of any of them. Alternatively, according to the embodiments of the present invention, one or more of the modules, submodules, units, and subunits can be at least partially implemented as computer program modules, and when the computer program modules are run, the corresponding functions can be performed.

[0148] For example, any multiple of the acquisition module 510, the extraction module 520, the fragmentation module 530, the encryption module 540, the sending module 550, the first receiving module 560, the second receiving module 610, the decryption module 620, the identification module 630 and the sending module 640 can be combined into one module for implementation, or any one of the modules can be split into multiple modules. Alternatively, at least part of the functions of one or more of these modules can be combined with at least part of the functions of other modules and implemented in one module. According to an embodiment of the present disclosure, at least one of the acquisition module 510, the extraction module 520, the slicing module 530, the encryption module 540, the sending module 550, the first receiving module 560, the second receiving module 610, the decryption module 620, the identification module 630 and the sending module 640 can be at least partially implemented as a hardware circuit, such as a field programmable gate array (FPGA), a programmable logic array (PLA), a system on a chip, a system on a substrate, a system on a package, an application-specific integrated circuit (ASIC), or can be implemented by hardware or firmware such as any other reasonable way of integrating or packaging the circuit, or by any one of the three implementation methods of software, hardware and firmware or by an appropriate combination of any of them. Alternatively, at least one of the acquisition module 510, the extraction module 520, the slicing module 530, the encryption module 540, the sending module 550, the first receiving module 560, the second receiving module 610, the decryption module 620, the identification module 630 and the sending module 640 can be at least partially implemented as a computer program module, and when the computer program module is run, the corresponding function can be performed.

[0149] Figure 8The block diagram of a computer system suitable for implementing the method described above according to an embodiment of the present disclosure is schematically shown. Figure 8 The computer system shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present disclosure.

[0150] like Figure 8 As shown, the computer system 800 according to the embodiment of the present disclosure includes a processor 801, which can perform various appropriate actions and processes according to the program stored in the read-only memory (ROM) 802 or the program loaded from the storage part 808 to the random access memory (RAM) 803. The processor 801 may include, for example, a general-purpose microprocessor (such as a CPU), an instruction set processor and / or a related chipset and / or a special-purpose microprocessor (for example, an application-specific integrated circuit (ASIC)), etc. The processor 801 may also include an onboard memory for caching purposes. The processor 801 may include a single processing unit or multiple processing units for performing different actions of the method flow according to the embodiment of the present disclosure.

[0151] In RAM 803, various programs and data required for the operation of system 800 are stored. Processor 801, ROM 802 and RAM 803 are connected to each other through bus 804. Processor 801 performs various operations of the method flow according to the embodiment of the present disclosure by executing the program in ROM 802 and / or RAM 803. It should be noted that the program can also be stored in one or more memories other than ROM 802 and RAM 803. Processor 801 can also perform various operations of the method flow according to the embodiment of the present disclosure by executing the program stored in one or more memories.

[0152] According to an embodiment of the present disclosure, the system 800 may further include an input / output (I / O) interface 805, which is also connected to the bus 804. The system 800 may further include one or more of the following components connected to the I / O interface 805: an input section 806 including a keyboard, a mouse, etc.; an output section 807 including a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker, etc.; a storage section 808 including a hard disk, etc.; and a communication section 809 including a network interface card such as a LAN card, a modem, etc. The communication section 809 performs communication processing via a network such as the Internet. A drive 810 is also connected to the I / O interface 805 as needed. A removable medium 811, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 810 as needed, so that a computer program read therefrom is installed into the storage section 808 as needed.

[0153] An embodiment of the present disclosure also includes a computer program product, which includes a computer program, and the computer program contains a program code for executing the method provided by the embodiment of the present disclosure. When the computer program product is run on an electronic device, the program code is used to enable the electronic device to implement the method for recognizing iris images provided by the embodiment of the present disclosure.

[0154] When the computer program is executed by the processor 801, the above functions defined in the system / device of the embodiment of the present disclosure are executed. According to the embodiment of the present disclosure, the system, device, module, unit, etc. described above can be implemented by a computer program module. In one embodiment, the computer program can rely on tangible storage media such as optical storage devices and magnetic storage devices. In another embodiment, the computer program can also be transmitted and distributed in the form of a signal on a network medium, and downloaded and installed through the communication part 809, and / or installed from a removable medium 811. The program code contained in the computer program can be transmitted using any appropriate network medium, including but not limited to: wireless, wired, etc., or any suitable combination of the above.

[0155] According to an embodiment of the present disclosure, the program code for executing the computer program provided by the embodiment of the present disclosure can be written in any combination of one or more programming languages. Specifically, these computing programs can be implemented using high-level process and / or object-oriented programming languages, and / or assembly / machine languages. Programming languages ​​include, but are not limited to, Java, C++, python, "C" language or similar programming languages. The program code can be executed entirely on the user computing device, partially on the user device, partially on the remote computing device, or entirely on the remote computing device or server. In the case of a remote computing device, the remote computing device can be connected to the user computing device through any type of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computing device (for example, using an Internet service provider to connect through the Internet).

[0156] The present disclosure also provides a computer-readable storage medium, which may be included in the device / apparatus / system described in the above embodiments; or may exist independently without being assembled into the device / apparatus / system. The above computer-readable storage medium carries one or more programs, and when the above one or more programs are executed, the method according to the embodiment of the present disclosure is implemented.

[0157] According to an embodiment of the present disclosure, the computer-readable storage medium may be a non-volatile computer-readable storage medium, for example, may include but is not limited to: a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In the present disclosure, a computer-readable storage medium may be any tangible medium containing or storing a program, which may be used by or in combination with an instruction execution system, an apparatus or a device. For example, according to an embodiment of the present disclosure, a computer-readable storage medium may include the ROM 802 and / or RAM 803 described above and / or one or more memories other than ROM 802 and RAM 803.

[0158] The flow charts and block diagrams in the accompanying drawings illustrate the possible architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each box in the flow chart or block diagram can represent a module, a program segment, or a part of a code, and the above-mentioned module, program segment, or a part of a code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram or flow chart, and the combination of the boxes in the block diagram or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0159] It will be appreciated by those skilled in the art that the features described in the various embodiments and / or claims of the present disclosure may be combined and / or combined in a variety of ways, even if such combinations and / or combinations are not explicitly described in the present disclosure. In particular, the features described in the various embodiments and / or claims of the present disclosure may be combined and / or combined in a variety of ways without departing from the spirit and teachings of the present disclosure. All of these combinations and / or combinations fall within the scope of the present disclosure.

[0160] The embodiments of the present disclosure are described above. However, these embodiments are only for the purpose of illustration and are not intended to limit the scope of the present disclosure. Although the embodiments are described above separately, this does not mean that the measures in the various embodiments cannot be used in combination to advantage. The scope of the present disclosure is defined by the attached claims and their equivalents. Without departing from the scope of the present disclosure, those skilled in the art may make various substitutions and modifications, which should all fall within the scope of the present disclosure.

Claims

1. A method for recognizing an iris image, comprising: Obtaining an iris image to be recognized; Extracting iris texture feature data of the iris image to be identified by using a preset filter; Determine a plurality of fragmentation data according to the iris texture feature data, The plurality of slice data includes first slice data and second slice data; and the determining the plurality of slice data according to the iris texture feature data includes: Generate first fragment data having the same dimension as the iris texture feature data based on the iris texture feature data according to a random generation algorithm; and Performing a preset operation on the iris texture feature data and the first fragmentation data to obtain second fragmentation data having the same dimension as the iris texture feature data; Encrypting the multiple slice data to obtain multiple ciphertext slice data; Sending the plurality of ciphertext fragment data to a server device, so that the server device generates a recognition result for the iris image to be recognized according to the plurality of ciphertext fragment data; and Receive the recognition result from the server device.

2. The method according to claim 1, wherein: The step of extracting iris texture feature data of the iris image to be identified by using a preset filter comprises: performing normalization processing on the iris image to be recognized; and The preset filter is used to extract features from the normalized iris image to be identified, so as to obtain iris texture feature data of the iris image to be identified.

3. The method according to claim 2, wherein: The preset filter is a two-dimensional Gabor filter; the method further includes: The two-dimensional Gabor filter G is generated according to the following formula: ， Among them, the is the center position of the two-dimensional Gabor filter, and r, , , , is a positional parameter.

4. The method according to claim 1, wherein: The step of generating first fragment data having the same dimension as the iris texture feature data based on the iris texture feature data according to a random generation algorithm comprises: randomly determining a target operation according to a random generation algorithm; and The target operation is performed on each element in the iris texture feature data to obtain an operation result having the same dimension as the iris texture feature data as the first fragment data.

5. The method according to claim 1, wherein: The preset operation is a difference operation; performing the preset operation on the iris texture feature data and the first fragmentation data to obtain second fragmentation data having the same dimension as the iris texture feature data includes: The difference between each element in the iris texture feature data and the element corresponding to the element in the first fragment data is calculated to obtain a plurality of difference values ​​as the second fragment data.

6. The method according to claim 1, wherein: The multiple ciphertext fragment data include first ciphertext fragment data and second ciphertext fragment data; The encrypting the plurality of fragmented data to obtain a plurality of ciphertext fragmented data comprises: The first fragmented data is encrypted according to a first encryption algorithm to obtain first ciphertext fragmented data, and the second fragmented data is encrypted according to a second encryption algorithm to obtain second ciphertext fragmented data.

7. The method according to claim 1, wherein: The obtaining of the iris image to be identified comprises: Collecting original iris images; Performing iris liveness detection and / or image quality detection on the original iris image; and An original iris image that passes the iris liveness detection and / or image quality detection is determined as the iris image to be recognized.

8. The method according to any one of claims 1 to 7, wherein: The method is applied to a client device.

9. A method for recognizing an iris image, comprising: Receiving a plurality of ciphertext fragment data from a client device, wherein each of the plurality of ciphertext fragment data contains texture feature information of an iris image to be identified; Decrypt the multiple ciphertext fragmented data to obtain multiple fragmented data, The plurality of slice data include first slice data and second slice data; the client device determines, based on the iris texture feature data of the iris image to be identified, that the plurality of slice data include: Generate first fragment data having the same dimension as the iris texture feature data based on the iris texture feature data according to a random generation algorithm; and Performing a preset operation on the iris texture feature data and the first fragmentation data to obtain second fragmentation data having the same dimension as the iris texture feature data; Distributing the plurality of slice data to a plurality of computing nodes, so that the plurality of slice data are recognized by the plurality of computing nodes to obtain recognition results for the iris image to be recognized; and The recognition result is sent to the client device.

10. The method according to claim 9, wherein: The multiple ciphertext fragment data include first ciphertext fragment data and second ciphertext fragment data; The decrypting the plurality of ciphertext fragmented data to obtain the plurality of fragmented data comprises: According to the first encryption algorithm, the first ciphertext fragment data is decrypted to obtain the first fragment data, and according to the second encryption algorithm, the second ciphertext fragment data is decrypted to obtain the second fragment data.

11. The method according to claim 10, wherein: The step of distributing the plurality of slice data to a plurality of computing nodes so as to identify the plurality of slice data through the plurality of computing nodes and obtain a recognition result for the iris image to be recognized includes: Allocate a first computing node to the first shard data, and allocate a second computing node to the second shard data; Acquire the first shard data through the first computing node, and calculate a first similarity between the first shard data and a pre-stored iris feature; Acquire the second slice data through the second computing node, and calculate a second similarity between the second slice data and the pre-stored iris feature; and The recognition result is determined according to the first similarity and the second similarity.

12. The method according to claim 11, further comprising: Storing the first fragment data in a first data cache space, and storing the second fragment data in a second data cache space, wherein the first data cache space and the second data cache space belong to different management domains; Wherein, obtaining the first shard data through the first computing node includes: reading the first shard data in the first data cache space through the first computing node; The acquiring the second shard data through the second computing node includes: reading the second shard data in the second data cache space through the second computing node.

13. The method according to any one of claims 9 to 12, wherein: The method is applied to a server device.

14. A device for recognizing an iris image, comprising: An acquisition module, used for acquiring an iris image to be recognized; An extraction module, used for extracting iris texture feature data of the iris image to be identified by using a preset filter; A slicing module is used to determine a plurality of slicing data according to the iris texture feature data, The plurality of slice data includes first slice data and second slice data; and the determining the plurality of slice data according to the iris texture feature data includes: Generate first fragment data having the same dimension as the iris texture feature data based on the iris texture feature data according to a random generation algorithm; and Performing a preset operation on the iris texture feature data and the first fragmentation data to obtain second fragmentation data having the same dimension as the iris texture feature data; An encryption module, used for encrypting the plurality of slice data to obtain a plurality of ciphertext slice data; a sending module, configured to send the plurality of ciphertext fragment data to a server device, so that the server device generates a recognition result for the iris image to be recognized according to the plurality of ciphertext fragment data; and The first receiving module is used to receive the recognition result from the server device.

15. A device for recognizing an iris image, comprising: A second receiving module is used to receive a plurality of ciphertext fragment data from a client device, each of the plurality of ciphertext fragment data contains texture feature information of an iris image to be identified; A decryption module is used to decrypt the plurality of ciphertext fragmented data to obtain a plurality of fragmented data. The plurality of slice data include first slice data and second slice data; the client device determines, based on the iris texture feature data of the iris image to be identified, that the plurality of slice data include: Generate first fragment data having the same dimension as the iris texture feature data based on the iris texture feature data according to a random generation algorithm; and Performing a preset operation on the iris texture feature data and the first fragmentation data to obtain second fragmentation data having the same dimension as the iris texture feature data; an identification module, configured to distribute the plurality of slice data to a plurality of computing nodes, so as to identify the plurality of slice data through the plurality of computing nodes, and obtain an identification result for the iris image to be identified; and A sending module is used to send the recognition result to the client device.

16. A computing device comprising: one or more processors; a memory 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 the method according to any one of claims 1 to 13.

17. A computer-readable storage medium storing computer-executable instructions, wherein the instructions are used to implement the method according to any one of claims 1 to 13 when executed.

18. A computer program product comprising computer executable instructions for implementing the method according to any one of claims 1 to 13 when the instructions are executed.

Images